Junaid Qadir

Mahdi Alkaeed, Adnan Qayyum, Nabeel Abo Kashreef et al.

Large Language Models (LLMs) are increasingly used in clinical applications. However, their behavior remains highly sensitive to subtle linguistic variations, such as rephrasing or syntactic variation. This sensitivity poses risks in safety-critical healthcare settings, where semantically equivalent inputs should produce consistent predictions. However, a key challenge is to ensure that prompt variations truly preserve clinical meaning, as embedding-based similarity metrics often fail to capture distinctions involving negation, temporality, or severity. To address this limitation, we propose a semantic verification framework based on Natural Language Inference (NLI) to filter meaning-preserving prompt variations, which are further refined using an LLM-as-a-judge and audited by a clinical expert. In addition, we introduce three metrics to quantify model sensitivity: MeaningPreserving Variation Sensitivity (MVS), confidence variation (ΔC), and Worst-Case Instability (WCI). We evaluate 16 open-source general-purpose (GP) and medical LLMs within the same model families and parameter scales, using reformulated prompts derived from the DiagnosisQA and MedQA datasets. Our results demonstrate that robustness differences between domain-specific (DS) models are mixed and highly model-dependent, i.e., domain specialization does not consistently improve or reduce robustness to meaning-preserving prompt reformulations. Several DS models rank among the most robust (when compared with GP counterparts), and strong GP baselines remain competitive as well.

Siddique Latif, Aun Zaidi, Heriberto Cuayahuitl et al.

The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their potential for modeling long-range dependencies within speech sequences. Recently, transformers have gained prominence across various speech-related domains, including automatic speech recognition, speech synthesis, speech translation, speech para-linguistics, speech enhancement, spoken dialogue systems, and numerous multimodal applications. In this paper, we present a comprehensive survey that aims to bridge research studies from diverse subfields within speech technology. By consolidating findings from across the speech technology landscape, we provide a valuable resource for researchers interested in harnessing the power of transformers to advance the field. We identify the challenges encountered by transformers in speech processing while also offering insights into potential solutions to address these issues.

Adnan Qayyum, Muhammad Atif Butt, Hassan Ali et al.

Metaverse is expected to emerge as a new paradigm for the next-generation Internet, providing fully immersive and personalised experiences to socialize, work, and play in self-sustaining and hyper-spatio-temporal virtual world(s). The advancements in different technologies like augmented reality, virtual reality, extended reality (XR), artificial intelligence (AI), and 5G/6G communication will be the key enablers behind the realization of AI-XR metaverse applications. While AI itself has many potential applications in the aforementioned technologies (e.g., avatar generation, network optimization, etc.), ensuring the security of AI in critical applications like AI-XR metaverse applications is profoundly crucial to avoid undesirable actions that could undermine users' privacy and safety, consequently putting their lives in danger. To this end, we attempt to analyze the security, privacy, and trustworthiness aspects associated with the use of various AI techniques in AI-XR metaverse applications. Specifically, we discuss numerous such challenges and present a taxonomy of potential solutions that could be leveraged to develop secure, private, robust, and trustworthy AI-XR applications. To highlight the real implications of AI-associated adversarial threats, we designed a metaverse-specific case study and analyzed it through the adversarial lens. Finally, we elaborate upon various open issues that require further research interest from the community.

Mohammed Aledhari, Mohamed Rahouti, Junaid Qadir et al.

This article outlines the architecture of autonomous driving and related complementary frameworks from the perspective of human comfort. The technical elements for measuring Autonomous Vehicle (AV) user comfort and psychoanalysis are listed here. At the same time, this article introduces the technology related to the structure of automatic driving and the reaction time of automatic driving. We also discuss the technical details related to the automatic driving comfort system, the response time of the AV driver, the comfort level of the AV, motion sickness, and related optimization technologies. The function of the sensor is affected by various factors. Since the sensor of automatic driving mainly senses the environment around a vehicle, including "the weather" which introduces the challenges and limitations of second-hand sensors in autonomous vehicles under different weather conditions. The comfort and safety of autonomous driving are also factors that affect the development of autonomous driving technologies. This article further analyzes the impact of autonomous driving on the user's physical and psychological states and how the comfort factors of autonomous vehicles affect the automotive market. Also, part of our focus is on the benefits and shortcomings of autonomous driving. The goal is to present an exhaustive overview of the most relevant technical matters to help researchers and application developers comprehend the different comfort factors and systems of autonomous driving. Finally, we provide detailed automated driving comfort use cases to illustrate the comfort-related issues of autonomous driving. Then, we provide implications and insights for the future of autonomous driving.

Syed Aun Muhammad Zaidi, Siddique Latif, Junaid Qadir

Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems are unable to achieve improved performance in cross-language settings. In this paper, we propose a Multimodal Dual Attention Transformer (MDAT) model to improve cross-language SER. Our model utilises pre-trained models for multimodal feature extraction and is equipped with a dual attention mechanism including graph attention and co-attention to capture complex dependencies across different modalities and achieve improved cross-language SER results using minimal target language data. In addition, our model also exploits a transformer encoder layer for high-level feature representation to improve emotion classification accuracy. In this way, MDAT performs refinement of feature representation at various stages and provides emotional salient features to the classification layer. This novel approach also ensures the preservation of modality-specific emotional information while enhancing cross-modality and cross-language interactions. We assess our model's performance on four publicly available SER datasets and establish its superior effectiveness compared to recent approaches and baseline models.

Shawqi Al-Maliki, Adnan Qayyum, Hassan Ali et al.

Deep Neural Networks (DNNs) have been the driving force behind many of the recent advances in machine learning. However, research has shown that DNNs are vulnerable to adversarial examples -- input samples that have been perturbed to force DNN-based models to make errors. As a result, Adversarial Machine Learning (AdvML) has gained a lot of attention, and researchers have investigated these vulnerabilities in various settings and modalities. In addition, DNNs have also been found to incorporate embedded bias and often produce unexplainable predictions, which can result in anti-social AI applications. The emergence of new AI technologies that leverage Large Language Models (LLMs), such as ChatGPT and GPT-4, increases the risk of producing anti-social applications at scale. AdvML for Social Good (AdvML4G) is an emerging field that repurposes the AdvML bug to invent pro-social applications. Regulators, practitioners, and researchers should collaborate to encourage the development of pro-social applications and hinder the development of anti-social ones. In this work, we provide the first comprehensive review of the emerging field of AdvML4G. This paper encompasses a taxonomy that highlights the emergence of AdvML4G, a discussion of the differences and similarities between AdvML4G and AdvML, a taxonomy covering social good-related concepts and aspects, an exploration of the motivations behind the emergence of AdvML4G at the intersection of ML4G and AdvML, and an extensive summary of the works that utilize AdvML4G as an auxiliary tool for innovating pro-social applications. Finally, we elaborate upon various challenges and open research issues that require significant attention from the research community.

Mahdi Alkaeed, Adnan Qayyum, Junaid Qadir

The metaverse is a nascent concept that envisions a virtual universe, a collaborative space where individuals can interact, create, and participate in a wide range of activities. Privacy in the metaverse is a critical concern as the concept evolves and immersive virtual experiences become more prevalent. The metaverse privacy problem refers to the challenges and concerns surrounding the privacy of personal information and data within Virtual Reality (VR) environments as the concept of a shared VR space becomes more accessible. Metaverse will harness advancements from various technologies such as Artificial Intelligence (AI), Extended Reality (XR), Mixed Reality (MR), and 5G/6G-based communication to provide personalized and immersive services to its users. Moreover, to enable more personalized experiences, the metaverse relies on the collection of fine-grained user data that leads to various privacy issues. Therefore, before the potential of the metaverse can be fully realized, privacy concerns related to personal information and data within VR environments must be addressed. This includes safeguarding users' control over their data, ensuring the security of their personal information, and protecting in-world actions and interactions from unauthorized sharing. In this paper, we explore various privacy challenges that future metaverses are expected to face, given their reliance on AI for tracking users, creating XR and MR experiences, and facilitating interactions. Moreover, we thoroughly analyze technical solutions such as differential privacy, Homomorphic Encryption (HE), and Federated Learning (FL) and discuss related sociotechnical issues regarding privacy.

Adnan Qayyum, Muhammad Bilal, Muhammad Hadi et al.

Recent advancements in technology, particularly in machine learning (ML), deep learning (DL), and the metaverse, offer great potential for revolutionizing surgical science. The combination of artificial intelligence and extended reality (AI-XR) technologies has the potential to create a surgical metaverse, a virtual environment where surgeries can be planned and performed. This paper aims to provide insight into the various potential applications of an AI-XR surgical metaverse and the challenges that must be addressed to bring its full potential to fruition. It is important for the community to focus on these challenges to fully realize the potential of the AI-XR surgical metaverses. Furthermore, to emphasize the need for secure and robust AI-XR surgical metaverses and to demonstrate the real-world implications of security threats to the AI-XR surgical metaverses, we present a case study in which the ``an immersive surgical attack'' on incision point localization is performed in the context of preoperative planning in a surgical metaverse.

Sofiat Abioye, Ufaq Khan, Shazad Ashraf et al.

Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present PathWISE, a five-phase pipeline combining four LLM-based agents with a deterministic depth-first search auditor and a Java compiler critic, transforming these non-computable artefacts into validated, executable HL7 Clinical Quality Language (CQL) libraries deployable as FHIR CDS Hooks services. Purpose-built agents extract flowchart structure into a typed directed graph, perform deterministic path enumeration, conduct a structured semantic audit of every node's computability, generate terminology-constrained CQL definitions verified by the official Java CQL-to-ELM compiler, and produce routing logic covering 100% of enumerated patient journeys. Demonstrated across five UK NHS cancer pathways (colorectal, lung, skin, upper GI, and breast), PathWISE audits up to 183 nodes (182 under the Hybrid configuration), identifies 544 structured governance findings across four issue categories, achieves 100% syntactic compilation success, with UNCOMPUTABLE nodes receiving false placeholders that preserve compilability while surfacing governance gaps for clinical review, and produces zero hallucinated terminology codes for dictionary-covered concepts. Critically, PathWISE confines non-deterministic LLM inference to knowledge extraction while deterministic graph mathematics and a standard compiler underpin every verification step.

Shawqi Al-Maliki, Faissal El Bouanani, Mohamed Abdallah et al.

Data distribution shift is a common problem in machine learning-powered smart city applications where the test data differs from the training data. Augmenting smart city applications with online machine learning models can handle this issue at test time, albeit with high cost and unreliable performance. To overcome this limitation, we propose to endow test-time adaptation with a systematic active fine-tuning (SAF) layer that is characterized by three key aspects: a continuity aspect that adapts to ever-present data distribution shifts; intelligence aspect that recognizes the importance of fine-tuning as a distribution-shift-aware process that occurs at the appropriate time to address the recently detected data distribution shifts; and cost-effectiveness aspect that involves budgeted human-machine collaboration to make relabeling cost-effective and practical for diverse smart city applications. Our empirical results show that our proposed approach outperforms the traditional test-time adaptation by a factor of two.

Hassan Ali, Adnan Qayyum, Ala Al-Fuqaha et al.

Several membership inference (MI) attacks have been proposed to audit a target DNN. Given a set of subjects, MI attacks tell which subjects the target DNN has seen during training. This work focuses on the post-training MI attacks emphasizing high confidence membership detection -- True Positive Rates (TPR) at low False Positive Rates (FPR). Current works in this category -- likelihood ratio attack (LiRA) and enhanced MI attack (EMIA) -- only perform well on complex datasets (e.g., CIFAR-10 and Imagenet) where the target DNN overfits its train set, but perform poorly on simpler datasets (0% TPR by both attacks on Fashion-MNIST, 2% and 0% TPR respectively by LiRA and EMIA on MNIST at 1% FPR). To address this, firstly, we unify current MI attacks by presenting a framework divided into three stages -- preparation, indication and decision. Secondly, we utilize the framework to propose two novel attacks: (1) Adversarial Membership Inference Attack (AMIA) efficiently utilizes the membership and the non-membership information of the subjects while adversarially minimizing a novel loss function, achieving 6% TPR on both Fashion-MNIST and MNIST datasets; and (2) Enhanced AMIA (E-AMIA) combines EMIA and AMIA to achieve 8% and 4% TPRs on Fashion-MNIST and MNIST datasets respectively, at 1% FPR. Thirdly, we introduce two novel augmented indicators that positively leverage the loss information in the Gaussian neighborhood of a subject. This improves TPR of all four attacks on average by 2.5% and 0.25% respectively on Fashion-MNIST and MNIST datasets at 1% FPR. Finally, we propose simple, yet novel, evaluation metric, the running TPR average (RTA) at a given FPR, that better distinguishes different MI attacks in the low FPR region. We also show that AMIA and E-AMIA are more transferable to the unknown DNNs (other than the target DNN) and are more robust to DP-SGD training as compared to LiRA and EMIA.

Hassan Ali, Muhammad Atif Butt, Fethi Filali et al.

Recent works have shown that deep learning (DL) models can effectively learn city-wide crowd-flow patterns, which can be used for more effective urban planning and smart city management. However, DL models have been known to perform poorly on inconspicuous adversarial perturbations. Although many works have studied these adversarial perturbations in general, the adversarial vulnerabilities of deep crowd-flow prediction models in particular have remained largely unexplored. In this paper, we perform a rigorous analysis of the adversarial vulnerabilities of DL-based crowd-flow prediction models under multiple threat settings, making three-fold contributions. (1) We propose CaV-detect by formally identifying two novel properties - Consistency and Validity - of the crowd-flow prediction inputs that enable the detection of standard adversarial inputs with 0% false acceptance rate (FAR). (2) We leverage universal adversarial perturbations and an adaptive adversarial loss to present adaptive adversarial attacks to evade CaV-detect defense. (3) We propose CVPR, a Consistent, Valid and Physically-Realizable adversarial attack, that explicitly inducts the consistency and validity priors in the perturbation generation mechanism. We find out that although the crowd-flow models are vulnerable to adversarial perturbations, it is extremely challenging to simulate these perturbations in physical settings, notably when CaV-detect is in place. We also show that CVPR attack considerably outperforms the adaptively modified standard attacks in FAR and adversarial loss metrics. We conclude with useful insights emerging from our work and highlight promising future research directions.

Muhammad Atif Butt, Hassan Ali, Adnan Qayyum et al.

Semantic understanding of roadways is a key enabling factor for safe autonomous driving. However, existing autonomous driving datasets provide well-structured urban roads while ignoring unstructured roadways containing distress, potholes, water puddles, and various kinds of road patches i.e., earthen, gravel etc. To this end, we introduce Road Region Segmentation dataset (R2S100K) -- a large-scale dataset and benchmark for training and evaluation of road segmentation in aforementioned challenging unstructured roadways. R2S100K comprises 100K images extracted from a large and diverse set of video sequences covering more than 1000 KM of roadways. Out of these 100K privacy respecting images, 14,000 images have fine pixel-labeling of road regions, with 86,000 unlabeled images that can be leveraged through semi-supervised learning methods. Alongside, we present an Efficient Data Sampling (EDS) based self-training framework to improve learning by leveraging unlabeled data. Our experimental results demonstrate that the proposed method significantly improves learning methods in generalizability and reduces the labeling cost for semantic segmentation tasks. Our benchmark will be publicly available to facilitate future research at https://r2s100k.github.io/.

Muhammad Bilal, Dinis Martinho, Reiner Sim et al.

Coronary angiography analysis is a common clinical task performed by cardiologists to diagnose coronary artery disease (CAD) through an assessment of atherosclerotic plaque's accumulation. This study introduces an end-to-end machine learning solution developed as part of our solution for the MICCAI 2023 Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) challenge, which aims to benchmark solutions for multivessel coronary artery segmentation and potential stenotic lesion localisation from X-ray coronary angiograms. We adopted a robust baseline model training strategy to progressively improve performance, comprising five successive stages of binary class pretraining, multivessel segmentation, fine-tuning using class frequency weighted dataloaders, fine-tuning using F1-based curriculum learning strategy (F1-CLS), and finally multi-target angiogram view classifier-based collective adaptation. Unlike many other medical imaging procedures, this task exhibits a notable degree of interobserver variability. %, making it particularly amenable to automated analysis. Our ensemble model combines the outputs from six baseline models using the weighted ensembling approach, which our analysis shows is found to double the predictive accuracy of the proposed solution. The final prediction was further refined, targeting the correction of misclassified blobs. Our solution achieved a mean F1 score of $37.69\%$ for coronary artery segmentation, and $39.41\%$ for stenosis localisation, positioning our team in the 5th position on both leaderboards. This work demonstrates the potential of automated tools to aid CAD diagnosis, guide interventions, and improve the accuracy of stent injections in clinical settings.

Naseem Machlovi, Maryam Saleki, Ruhul Amin et al.

As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater. While existing LLMs can detect dangerous or unsafe content, they often struggle with nuanced cases such as implicit offensiveness, subtle gender and racial biases, and jailbreak prompts, due to the subjective and context-dependent nature of these issues. Furthermore, their heavy reliance on training data can reinforce societal biases, resulting in inconsistent and ethically problematic outputs. To address these challenges, we introduce GuardEval, a unified multi-perspective benchmark dataset designed for both training and evaluation, containing 106 fine-grained categories spanning human emotions, offensive and hateful language, gender and racial bias, and broader safety concerns. We also present GemmaGuard (GGuard), a Quantized Low-Rank Adaptation (QLoRA), fine-tuned version of Gemma3-12B trained on GuardEval, to assess content moderation with fine-grained labels. Our evaluation shows that GGuard achieves a macro F1 score of 0.832, substantially outperforming leading moderation models, including OpenAI Moderator (0.64) and Llama Guard (0.61). We show that multi-perspective, human-centered safety benchmarks are critical for mitigating inconsistent moderation decisions. GuardEval and GGuard together demonstrate that diverse, representative data materially improve safety, and adversarial robustness on complex, borderline cases.

Adnan Qayyum, Hassan Ali, Massimo Caputo et al.

Over the past few years, surgical data science has attracted substantial interest from the machine learning (ML) community. Various studies have demonstrated the efficacy of emerging ML techniques in analysing surgical data, particularly recordings of procedures, for digitizing clinical and non-clinical functions like preoperative planning, context-aware decision-making, and operating skill assessment. However, this field is still in its infancy and lacks representative, well-annotated datasets for training robust models in intermediate ML tasks. Also, existing datasets suffer from inaccurate labels, hindering the development of reliable models. In this paper, we propose a systematic methodology for developing robust models for surgical tool detection using noisy data. Our methodology introduces two key innovations: (1) an intelligent active learning strategy for minimal dataset identification and label correction by human experts; and (2) an assembling strategy for a student-teacher model-based self-training framework to achieve the robust classification of 14 surgical tools in a semi-supervised fashion. Furthermore, we employ weighted data loaders to handle difficult class labels and address class imbalance issues. The proposed methodology achieves an average F1-score of 85.88\% for the ensemble model-based self-training with class weights, and 80.88\% without class weights for noisy labels. Also, our proposed method significantly outperforms existing approaches, which effectively demonstrates its effectiveness.

Adam Byfield, William Poulett, Ben Wallace et al.

Machine learning (ML) models are becoming integral in healthcare technologies, presenting a critical need for formal assurance to validate their safety, fairness, robustness, and trustworthiness. These models are inherently prone to errors, potentially posing serious risks to patient health and could even cause irreparable harm. Traditional software assurance techniques rely on fixed code and do not directly apply to ML models since these algorithms are adaptable and learn from curated datasets through a training process. However, adapting established principles, such as boundary testing using synthetic test data can effectively bridge this gap. To this end, we present a novel technique called Mix-Up Boundary Analysis (MUBA) that facilitates evaluating image classifiers in terms of prediction fairness. We evaluated MUBA for two important medical imaging tasks -- brain tumour classification and breast cancer classification -- and achieved promising results. This research aims to showcase the importance of adapting traditional assurance principles for assessing ML models to enhance the safety and reliability of healthcare technologies. To facilitate future research, we plan to publicly release our code for MUBA.

Mahdi Alkaeed, Sofiat Abioye, Adnan Qayyum et al.

In response to the success of proprietary Large Language Models (LLMs) such as OpenAI's GPT-4, there is a growing interest in developing open, non-proprietary LLMs and AI foundation models (AIFMs) for transparent use in academic, scientific, and non-commercial applications. Despite their inability to match the refined functionalities of their proprietary counterparts, open models hold immense potential to revolutionize healthcare applications. In this paper, we examine the prospects of open-source LLMs and AIFMs for developing healthcare applications and make two key contributions. Firstly, we present a comprehensive survey of the current state-of-the-art open-source healthcare LLMs and AIFMs and introduce a taxonomy of these open AIFMs, categorizing their utility across various healthcare tasks. Secondly, to evaluate the general-purpose applications of open LLMs in healthcare, we present a case study on personalized prescriptions. This task is particularly significant due to its critical role in delivering tailored, patient-specific medications that can greatly improve treatment outcomes. In addition, we compare the performance of open-source models with proprietary models in settings with and without Retrieval-Augmented Generation (RAG). Our findings suggest that, although less refined, open LLMs can achieve performance comparable to proprietary models when paired with grounding techniques such as RAG. Furthermore, to highlight the clinical significance of LLMs-empowered personalized prescriptions, we perform subjective assessment through an expert clinician. We also elaborate on ethical considerations and potential risks associated with the misuse of powerful LLMs and AIFMs, highlighting the need for a cautious and responsible implementation in healthcare.

Muhammad Bilal, Mahmood Alam, Deepa Bapu et al.

Indexing endoscopic surgical videos is vital in surgical data science, forming the basis for systematic retrospective analysis and clinical performance evaluation. Despite its significance, current video analytics rely on manual indexing, a time-consuming process. Advances in computer vision, particularly deep learning, offer automation potential, yet progress is limited by the lack of publicly available, densely annotated surgical datasets. To address this, we present TEMSET-24K, an open-source dataset comprising 24,306 trans-anal endoscopic microsurgery (TEMS) video micro-clips. Each clip is meticulously annotated by clinical experts using a novel hierarchical labeling taxonomy encompassing phase, task, and action triplets, capturing intricate surgical workflows. To validate this dataset, we benchmarked deep learning models, including transformer-based architectures. Our in silico evaluation demonstrates high accuracy (up to 0.99) and F1 scores (up to 0.99) for key phases like Setup and Suturing. The STALNet model, tested with ConvNeXt, ViT, and SWIN V2 encoders, consistently segmented well-represented phases. TEMSET-24K provides a critical benchmark, propelling state-of-the-art solutions in surgical data science.

Junaid Qadir, Muhammad Adil Attique, Saleha Shoaib et al.

Engineering education faces a double disruption: traditional apprenticeship models that cultivated judgment and tacit skill are eroding, just as generative AI emerges as an informal coaching partner. This convergence rekindles long-standing questions in the philosophy of AI and cognition about the limits of computation, the nature of embodied rationality, and the distinction between information processing and wisdom. Building on this rich intellectual tradition, this paper examines whether AI chatbots can provide coaching that fosters mastery rather than merely delivering information. We synthesize critical perspectives from decades of scholarship on expertise, tacit knowledge, and human-machine interaction, situating them within the context of contemporary AI-driven education. Empirically, we report findings from a mixed-methods study (N = 75 students, N = 7 faculty) exploring the use of a coaching chatbot in engineering education. Results reveal a consistent boundary: participants accept AI for technical problem solving (convergent tasks; M = 3.84 on a 1-5 Likert scale) but remain skeptical of its capacity for moral, emotional, and contextual judgment (divergent tasks). Faculty express stronger concerns over risk (M = 4.71 vs. M = 4.14, p = 0.003), and privacy emerges as a key requirement, with 64-71 percent of participants demanding strict confidentiality. Our findings suggest that while generative AI can democratize access to cognitive and procedural support, it cannot replicate the embodied, value-laden dimensions of human mentorship. We propose a multiplex coaching framework that integrates human wisdom within expert-in-the-loop models, preserving the depth of apprenticeship while leveraging AI scalability to enrich the next generation of engineering education.

Shawqi Al-Maliki, Ammar Gharaibeh, Mohamed Rahouti et al.

Large Language Models (LLMs) have revolutionized the field of natural language processing. However, they exhibit some limitations, including a lack of reliability and transparency: they may hallucinate and fail to provide sources that support the generated output. Retrieval-Augmented Generation (RAG) was introduced to address such limitations in LLMs. One popular implementation, RAG-as-a-Service (RaaS), has shortcomings that hinder its adoption and accessibility. For instance, RaaS pricing is based on the number of submitted prompts, without considering whether the prompts are enriched by relevant chunks, i.e., text segments retrieved from a vector database, or the quality of the utilized chunks (i.e., their degree of relevance). This results in an opaque and less cost-effective payment model. We propose Chunk-as-a-Service (CaaS) as a transparent and cost-effective alternative. CaaS includes two variants: Open-Budget CaaS (OB-CaaS) and Limited-Budget CaaS (LB-CaaS), which is enabled by our ``Utility-Cost Online Selection Algorithm (UCOSA)''. UCOSA further extends the cost-effectiveness and the accessibility of the OB-CaaS variant by enriching, in an online manner, a subset of the submitted prompts based on budget constraints and utility-cost tradeoff. Our experiments demonstrate the efficacy of the proposed UCOSA compared to both offline and relevance-greedy selection baselines. In terms of the performance metric-the number of enriched prompts (NEP) multiplied by the Average Relevance (AR)-UCOSA outperforms random selection by approximately 52% and achieves around 75% of the performance of offline selection methods. Additionally, in terms of budget utilization, LB-CaaS and OB-CaaS achieve higher performance-to-budget ratios of 140% and 86%, respectively, compared to RaaS, indicating their superior efficiency.

Abdullah Mushtaq, Muhammad Rafay Naeem, Ibrahim Ghaznavi et al.

Multi-Agent Large Language Models (LLMs) are gaining significant attention for their ability to harness collective intelligence in complex problem-solving, decision-making, and planning tasks. This aligns with the concept of the wisdom of crowds, where diverse agents contribute collectively to generating effective solutions, making it particularly suitable for educational settings. Senior design projects, also known as capstone or final year projects, are pivotal in engineering education as they integrate theoretical knowledge with practical application, fostering critical thinking, teamwork, and real-world problem-solving skills. In this paper, we explore the use of Multi-Agent LLMs in supporting these senior design projects undertaken by engineering students, which often involve multidisciplinary considerations and conflicting objectives, such as optimizing technical performance while addressing ethical, social, and environmental concerns. We propose a framework where distinct LLM agents represent different expert perspectives, such as problem formulation agents, system complexity agents, societal and ethical agents, or project managers, thus facilitating a holistic problem-solving approach. This implementation leverages standard multi-agent system (MAS) concepts such as coordination, cooperation, and negotiation, incorporating prompt engineering to develop diverse personas for each agent. These agents engage in rich, collaborative dialogues to simulate human engineering teams, guided by principles from swarm AI to efficiently balance individual contributions towards a unified solution. We adapt these techniques to create a collaboration structure for LLM agents, encouraging interdisciplinary reasoning and negotiation similar to real-world senior design projects. To assess the efficacy of this framework, we collected six proposals of engineering and computer science of...

Aos Mulahuwaish, Basheer Qolomany, Kevin Gyorick et al.

In today's digital era, the Internet, especially social media platforms, plays a significant role in shaping public opinions, attitudes, and beliefs. Unfortunately, the credibility of scientific information sources is often undermined by the spread of misinformation through various means, including technology-driven tools like bots, cyborgs, trolls, sock-puppets, and deep fakes. This manipulation of public discourse serves antagonistic business agendas and compromises civil society. In response to this challenge, a new scientific discipline has emerged: social cybersecurity.

Mohammed Aledhari, Rehma Razzak, Mohamed Rahouti et al.

The advancements in autonomous driving technology, coupled with the growing interest from automotive manufacturers and tech companies, suggest a rising adoption of Connected Autonomous Vehicles (CAVs) in the near future. Despite some evidence of higher accident rates in AVs, these incidents tend to result in less severe injuries compared to traditional vehicles due to cooperative safety measures. However, the increased complexity of CAV systems exposes them to significant security vulnerabilities, potentially compromising their performance and communication integrity. This paper contributes by presenting a detailed analysis of existing security frameworks and protocols, focusing on intra- and inter-vehicle communications. We systematically evaluate the effectiveness of these frameworks in addressing known vulnerabilities and propose a set of best practices for enhancing CAV communication security. The paper also provides a comprehensive taxonomy of attack vectors in CAV ecosystems and suggests future research directions for designing more robust security mechanisms. Our key contributions include the development of a new classification system for CAV security threats, the proposal of practical security protocols, and the introduction of use cases that demonstrate how these protocols can be integrated into real-world CAV applications. These insights are crucial for advancing secure CAV adoption and ensuring the safe integration of autonomous vehicles into intelligent transportation systems.

Abdullah Mushtaq, Muhammad Rafay Naeem, Muhammad Imran Taj et al.

As large language models (LLMs) like GPT-4 and Llama 3 become integral to educational contexts, concerns are mounting over the cultural biases, power imbalances, and ethical limitations embedded within these technologies. Though generative AI tools aim to enhance learning experiences, they often reflect values rooted in Western, Educated, Industrialized, Rich, and Democratic (WEIRD) cultural paradigms, potentially sidelining diverse global perspectives. This paper proposes a framework to assess and mitigate cultural bias within LLMs through the lens of applied multiplexity. Multiplexity, inspired by Senturk et al. and rooted in Islamic and other wisdom traditions, emphasizes the coexistence of diverse cultural viewpoints, supporting a multi-layered epistemology that integrates both empirical sciences and normative values. Our analysis reveals that LLMs frequently exhibit cultural polarization, with biases appearing in both overt responses and subtle contextual cues. To address inherent biases and incorporate multiplexity in LLMs, we propose two strategies: \textit{Contextually-Implemented Multiplex LLMs}, which embed multiplex principles directly into the system prompt, influencing LLM outputs at a foundational level and independent of individual prompts, and \textit{Multi-Agent System (MAS)-Implemented Multiplex LLMs}, where multiple LLM agents, each representing distinct cultural viewpoints, collaboratively generate a balanced, synthesized response. Our findings demonstrate that as mitigation strategies evolve from contextual prompting to MAS-implementation, cultural inclusivity markedly improves, evidenced by a significant rise in the Perspectives Distribution Score (PDS) and a PDS Entropy increase from 3.25\% at baseline to 98\% with the MAS-Implemented Multiplex LLMs. Sentiment analysis further shows a shift towards positive sentiment across cultures,...

Saad Hameed, Basheer Qolomany, Samir Brahim Belhaouari et al.

Determining the ideal architecture for deep learning models, such as the number of layers and neurons, is a difficult and resource-intensive process that frequently relies on human tuning or computationally costly optimization approaches. While Particle Swarm Optimization (PSO) and Large Language Models (LLMs) have been individually applied in optimization and deep learning, their combined use for enhancing convergence in numerical optimization tasks remains underexplored. Our work addresses this gap by integrating LLMs into PSO to reduce model evaluations and improve convergence for deep learning hyperparameter tuning. The proposed LLM-enhanced PSO method addresses the difficulties of efficiency and convergence by using LLMs (particularly ChatGPT-3.5 and Llama3) to improve PSO performance, allowing for faster achievement of target objectives. Our method speeds up search space exploration by substituting underperforming particle placements with best suggestions offered by LLMs. Comprehensive experiments across three scenarios -- (1) optimizing the Rastrigin function, (2) using Long Short-Term Memory (LSTM) networks for time series regression, and (3) using Convolutional Neural Networks (CNNs) for material classification -- show that the method significantly improves convergence rates and lowers computational costs. Depending on the application, computational complexity is lowered by 20% to 60% compared to traditional PSO methods. Llama3 achieved a 20% to 40% reduction in model calls for regression tasks, whereas ChatGPT-3.5 reduced model calls by 60% for both regression and classification tasks, all while preserving accuracy and error rates. This groundbreaking methodology offers a very efficient and effective solution for optimizing deep learning models, leading to substantial computational performance improvements across a wide range of applications.

Ufaq Khan, Umair Nawaz, Adnan Qayyum et al.

Recent advancements in machine learning (ML) and deep learning (DL), particularly through the introduction of Foundation Models (FMs), have significantly enhanced surgical scene understanding within minimally invasive surgery (MIS). This paper surveys the integration of state-of-the-art ML and DL technologies, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Foundation Models like the Segment Anything Model (SAM), into surgical workflows. These technologies improve segmentation accuracy, instrument tracking, and phase recognition in surgical scene understanding. The paper explores the challenges these technologies face, such as data variability and computational demands, and discusses ethical considerations and integration hurdles in clinical settings. Highlighting the roles of FMs, we bridge the technological capabilities with clinical needs and outline future research directions to enhance the adaptability, efficiency, and ethical alignment of AI applications in surgery. Our findings suggest that substantial progress has been made; however, more focused efforts are required to achieve seamless integration of these technologies into clinical workflows, ensuring they complement surgical practice by enhancing precision, reducing risks, and optimizing patient outcomes.

Abdullah Mushtaq, Imran Taj, Rafay Naeem et al.

Large Language Models (LLMs) are predominantly trained and aligned in ways that reinforce Western-centric epistemologies and socio-cultural norms, leading to cultural homogenization and limiting their ability to reflect global civilizational plurality. Existing benchmarking frameworks fail to adequately capture this bias, as they rely on rigid, closed-form assessments that overlook the complexity of cultural inclusivity. To address this, we introduce WorldView-Bench, a benchmark designed to evaluate Global Cultural Inclusivity (GCI) in LLMs by analyzing their ability to accommodate diverse worldviews. Our approach is grounded in the Multiplex Worldview proposed by Senturk et al., which distinguishes between Uniplex models, reinforcing cultural homogenization, and Multiplex models, which integrate diverse perspectives. WorldView-Bench measures Cultural Polarization, the exclusion of alternative perspectives, through free-form generative evaluation rather than conventional categorical benchmarks. We implement applied multiplexity through two intervention strategies: (1) Contextually-Implemented Multiplex LLMs, where system prompts embed multiplexity principles, and (2) Multi-Agent System (MAS)-Implemented Multiplex LLMs, where multiple LLM agents representing distinct cultural perspectives collaboratively generate responses. Our results demonstrate a significant increase in Perspectives Distribution Score (PDS) entropy from 13% at baseline to 94% with MAS-Implemented Multiplex LLMs, alongside a shift toward positive sentiment (67.7%) and enhanced cultural balance. These findings highlight the potential of multiplex-aware AI evaluation in mitigating cultural bias in LLMs, paving the way for more inclusive and ethically aligned AI systems.

Muhammad Umar Farooq, Abd Ur Rehman, Azka Rehman et al.

Accurate thyroid nodule segmentation in ultrasound images is critical for diagnosis and treatment planning. However, ambiguous boundaries between nodules and surrounding tissues, size variations, and the scarcity of annotated ultrasound data pose significant challenges for automated segmentation. Existing deep learning models struggle to incorporate contextual information from the thyroid gland and generalize effectively across diverse cases. To address these challenges, we propose SSMT-Net, a Semi-Supervised Multi-Task Transformer-based Network that leverages unlabeled data to enhance Transformer-centric encoder feature extraction capability in an initial unsupervised phase. In the supervised phase, the model jointly optimizes nodule segmentation, gland segmentation, and nodule size estimation, integrating both local and global contextual features. Extensive evaluations on the TN3K and DDTI datasets demonstrate that SSMT-Net outperforms state-of-the-art methods, with higher accuracy and robustness, indicating its potential for real-world clinical applications.

Abdullah Mushtaq, Rafay Naeem, Ezieddin Elmahjub et al.

Large language models are increasingly used for Islamic guidance, but risk misquoting texts, misapplying jurisprudence, or producing culturally inconsistent responses. We pilot an evaluation of GPT-4o, Ansari AI, and Fanar on prompts from authentic Islamic blogs. Our dual-agent framework uses a quantitative agent for citation verification and six-dimensional scoring (e.g., Structure, Islamic Consistency, Citations) and a qualitative agent for five-dimensional side-by-side comparison (e.g., Tone, Depth, Originality). GPT-4o scored highest in Islamic Accuracy (3.93) and Citation (3.38), Ansari AI followed (3.68, 3.32), and Fanar lagged (2.76, 1.82). Despite relatively strong performance, models still fall short in reliably producing accurate Islamic content and citations -- a paramount requirement in faith-sensitive writing. GPT-4o had the highest mean quantitative score (3.90/5), while Ansari AI led qualitative pairwise wins (116/200). Fanar, though trailing, introduces innovations for Islamic and Arabic contexts. This study underscores the need for community-driven benchmarks centering Muslim perspectives, offering an early step toward more reliable AI in Islamic knowledge and other high-stakes domains such as medicine, law, and journalism.

Abdullah Mushtaq, Muhammad Rafay Naeem, Ibrahim Ghaznavi et al.

Systematic Literature Reviews (SLRs) are foundational to evidence-based research but remain labor-intensive and prone to inconsistency across disciplines. We present an LLM-based SLR evaluation copilot built on a Multi-Agent System (MAS) architecture to assist researchers in assessing the overall quality of the systematic literature reviews. The system automates protocol validation, methodological assessment, and topic relevance checks using a scholarly database. Unlike conventional single-agent methods, our design integrates a specialized agentic approach aligned with PRISMA guidelines to support more structured and interpretable evaluations. We conducted an initial study on five published SLRs from diverse domains, comparing system outputs to expert-annotated PRISMA scores, and observed 84% agreement. While early results are promising, this work represents a first step toward scalable and accurate NLP-driven systems for interdisciplinary workflows and reveals their capacity for rigorous, domain-agnostic knowledge aggregation to streamline the review process.

Tamer Ahmed Eltaras, Qutaibah Malluhi, Alessandro Savino et al.

In the effort to learn from extensive collections of distributed data, federated learning has emerged as a promising approach for preserving privacy by using a gradient-sharing mechanism instead of exchanging raw data. However, recent studies show that private training data can be leaked through many gradient attacks. While previous analytical-based attacks have successfully reconstructed input data from fully connected layers, their effectiveness diminishes when applied to convolutional layers. This paper introduces an advanced data leakage method to efficiently exploit convolutional layers' gradients. We present a surprising finding: even with non-fully invertible activation functions, such as ReLU, we can analytically reconstruct training samples from the gradients. To the best of our knowledge, this is the first analytical approach that successfully reconstructs convolutional layer inputs directly from the gradients, bypassing the need to reconstruct layers' outputs. Prior research has mainly concentrated on the weight constraints of convolution layers, overlooking the significance of gradient constraints. Our findings demonstrate that existing analytical methods used to estimate the risk of gradient attacks lack accuracy. In some layers, attacks can be launched with less than 5% of the reported constraints.

Ghezlane Halhoul Merabet, Mohamed Essaaidi, Mohamed Ben Haddou et al.

Building operations represent a significant percentage of the total primary energy consumed in most countries due to the proliferation of Heating, Ventilation and Air-Conditioning (HVAC) installations in response to the growing demand for improved thermal comfort. Reducing the associated energy consumption while maintaining comfortable conditions in buildings are conflicting objectives and represent a typical optimization problem that requires intelligent system design. Over the last decade, different methodologies based on the Artificial Intelligence (AI) techniques have been deployed to find the sweet spot between energy use in HVAC systems and suitable indoor comfort levels to the occupants. This paper performs a comprehensive and an in-depth systematic review of AI-based techniques used for building control systems by assessing the outputs of these techniques, and their implementations in the reviewed works, as well as investigating their abilities to improve the energy-efficiency, while maintaining thermal comfort conditions. This enables a holistic view of (1) the complexities of delivering thermal comfort to users inside buildings in an energy-efficient way, and (2) the associated bibliographic material to assist researchers and experts in the field in tackling such a challenge. Among the 20 AI tools developed for both energy consumption and comfort control, functions such as identification and recognition patterns, optimization, predictive control. Based on the findings of this work, the application of AI technology in building control is a promising area of research and still an ongoing, i.e., the performance of AI-based control is not yet completely satisfactory. This is mainly due in part to the fact that these algorithms usually need a large amount of high-quality real-world data, which is lacking in the building or, more precisely, the energy sector.

Hafiz Shehbaz Ali, Fakhar ul Hassan, Siddique Latif et al.

Speech emotion sensing in communication networks has a wide range of applications in real life. In these applications, voice data are transmitted from the user to the central server for storage, processing, and decision making. However, speech data contain vulnerable information that can be used maliciously without the user's consent by an eavesdropping adversary. In this work, we present a privacy-enhanced emotion communication system for preserving the user personal information in emotion-sensing applications. We propose the use of an adversarial learning framework that can be deployed at the edge to unlearn the users' private information in the speech representations. These privacy-enhanced representations can be transmitted to the central server for decision making. We evaluate the proposed model on multiple speech emotion datasets and show that the proposed model can hide users' specific demographic information and improve the robustness of emotion identification without significantly impacting performance. To the best of our knowledge, this is the first work on a privacy-preserving framework for emotion sensing in the communication network.

Ahmed Rasheed, Muhammad Shahzad Younis, Junaid Qadir et al.

Breast cancer is one of the most common cause of deaths among women. Mammography is a widely used imaging modality that can be used for cancer detection in its early stages. Deep learning is widely used for the detection of cancerous masses in the images obtained via mammography. The need to improve accuracy remains constant due to the sensitive nature of the datasets so we introduce segmentation and wavelet transform to enhance the important features in the image scans. Our proposed system aids the radiologist in the screening phase of cancer detection by using a combination of segmentation and wavelet transforms as pre-processing augmentation that leads to transfer learning in neural networks. The proposed system with these pre-processing techniques significantly increases the accuracy of detection on Mini-MIAS.

Ahmed Rasheed, Muhammad Shahzad Younis, Farooq Ahmad et al.

Wheat is the main agricultural crop of Pakistan and is a staple food requirement of almost every Pakistani household making it the main strategic commodity of the country whose availability and affordability is the government's main priority. Wheat food availability can be vastly affected by multiple factors included but not limited to the production, consumption, financial crisis, inflation, or volatile market. The government ensures food security by particular policy and monitory arrangements, which keeps up purchase parity for the poor. Such arrangements can be made more effective if a dynamic analysis is carried out to estimate the future yield based on certain current factors. Future planning of commodity pricing is achievable by forecasting their future price anticipated by the current circumstances. This paper presents a wheat price forecasting methodology, which uses the price, weather, production, and consumption trends for wheat prices taken over the past few years and analyzes them with the help of advance neural networks architecture Long Short Term Memory (LSTM) networks. The proposed methodology presented significantly improved results versus other conventional machine learning and statistical time series analysis methods.

Kashif Ahmad, Firoj Alam, Junaid Qadir et al.

Contact tracing has been globally adopted in the fight to control the infection rate of COVID-19. Thanks to digital technologies, such as smartphones and wearable devices, contacts of COVID-19 patients can be easily traced and informed about their potential exposure to the virus. To this aim, several interesting mobile applications have been developed. However, there are ever-growing concerns over the working mechanism and performance of these applications. The literature already provides some interesting exploratory studies on the community's response to the applications by analyzing information from different sources, such as news and users' reviews of the applications. However, to the best of our knowledge, there is no existing solution that automatically analyzes users' reviews and extracts the evoked sentiments. In this work, we propose a pipeline starting from manual annotation via a crowd-sourcing study and concluding on the development and training of AI models for automatic sentiment analysis of users' reviews. In total, we employ eight different methods achieving up to an average F1-Scores 94.8% indicating the feasibility of automatic sentiment analysis of users' reviews on the COVID-19 contact tracing applications. We also highlight the key advantages, drawbacks, and users' concerns over the applications. Moreover, we also collect and annotate a large-scale dataset composed of 34,534 reviews manually annotated from the contract tracing applications of 46 distinct countries. The presented analysis and the dataset are expected to provide a baseline/benchmark for future research in the domain.

Adnan Qayyum, Kashif Ahmad, Muhammad Ahtazaz Ahsan et al.

Despite significant improvements over the last few years, cloud-based healthcare applications continue to suffer from poor adoption due to their limitations in meeting stringent security, privacy, and quality of service requirements (such as low latency). The edge computing trend, along with techniques for distributed machine learning such as federated learning, have gained popularity as a viable solution in such settings. In this paper, we leverage the capabilities of edge computing in medicine by analyzing and evaluating the potential of intelligent processing of clinical visual data at the edge allowing the remote healthcare centers, lacking advanced diagnostic facilities, to benefit from the multi-modal data securely. To this aim, we utilize the emerging concept of clustered federated learning (CFL) for an automatic diagnosis of COVID-19. Such an automated system can help reduce the burden on healthcare systems across the world that has been under a lot of stress since the COVID-19 pandemic emerged in late 2019. We evaluate the performance of the proposed framework under different experimental setups on two benchmark datasets. Promising results are obtained on both datasets resulting in comparable results against the central baseline where the specialized models (i.e., each on a specific type of COVID-19 imagery) are trained with central data, and improvements of 16\% and 11\% in overall F1-Scores have been achieved over the multi-modal model trained in the conventional Federated Learning setup on X-ray and Ultrasound datasets, respectively. We also discuss in detail the associated challenges, technologies, tools, and techniques available for deploying ML at the edge in such privacy and delay-sensitive applications.

Bilal Yousaf, Muhammad Usama, Waqas Sultani et al.

Rapid progress in adversarial learning has enabled the generation of realistic-looking fake visual content. To distinguish between fake and real visual content, several detection techniques have been proposed. The performance of most of these techniques however drops off significantly if the test and the training data are sampled from different distributions. This motivates efforts towards improving the generalization of fake detectors. Since current fake content generation techniques do not accurately model the frequency spectrum of the natural images, we observe that the frequency spectrum of the fake visual data contains discriminative characteristics that can be used to detect fake content. We also observe that the information captured in the frequency spectrum is different from that of the spatial domain. Using these insights, we propose to complement frequency and spatial domain features using a two-stream convolutional neural network architecture called TwoStreamNet. We demonstrate the improved generalization of the proposed two-stream network to several unseen generation architectures, datasets, and techniques. The proposed detector has demonstrated significant performance improvement compared to the current state-of-the-art fake content detectors and fusing the frequency and spatial domain streams has also improved generalization of the detector.

Muhammad Ahtazaz Ahsan, Adnan Qayyum, Junaid Qadir et al.

In recent years, deep learning (DL) techniques have provided state-of-the-art performance on different medical imaging tasks. However, the availability of good quality annotated medical data is very challenging due to involved time constraints and the availability of expert annotators, e.g., radiologists. In addition, DL is data-hungry and their training requires extensive computational resources. Another problem with DL is their black-box nature and lack of transparency on its inner working which inhibits causal understanding and reasoning. In this paper, we jointly address these challenges by proposing a hybrid model, which uses a Bayesian convolutional neural network (BCNN) for uncertainty quantification, and an active learning approach for annotating the unlabelled data. The BCNN is used as a feature descriptor and these features are then used for training a model, in an active learning setting. We evaluate the proposed framework for diabetic retinopathy classification problem and have achieved state-of-the-art performance in terms of different metrics.

Inaam Ilahi, Muhammad Usama, Muhammad Omer Farooq et al.

The anticipated increase in the count of IoT devices in the coming years motivates the development of efficient algorithms that can help in their effective management while keeping the power consumption low. In this paper, we propose an intelligent multi-channel resource allocation algorithm for dense LoRa networks termed LoRaDRL and provide a detailed performance evaluation. Our results demonstrate that the proposed algorithm not only significantly improves LoRaWAN's packet delivery ratio (PDR) but is also able to support mobile end-devices (EDs) while ensuring lower power consumption hence increasing both the lifetime and capacity of the network.} Most previous works focus on proposing different MAC protocols for improving the network capacity, i.e., LoRaWAN, delay before transmit etc. We show that through the use of LoRaDRL, we can achieve the same efficiency with ALOHA \textcolor{black}{compared to LoRaSim, and LoRa-MAB while moving the complexity from EDs to the gateway thus making the EDs simpler and cheaper. Furthermore, we test the performance of LoRaDRL under large-scale frequency jamming attacks and show its adaptiveness to the changes in the environment. We show that LoRaDRL's output improves the performance of state-of-the-art techniques resulting in some cases an improvement of more than 500\% in terms of PDR compared to learning-based techniques.

Kashif Ahmad, Majdi Maabreh, Mohamed Ghaly et al.

As the globally increasing population drives rapid urbanisation in various parts of the world, there is a great need to deliberate on the future of the cities worth living. In particular, as modern smart cities embrace more and more data-driven artificial intelligence services, it is worth remembering that technology can facilitate prosperity, wellbeing, urban livability, or social justice, but only when it has the right analog complements (such as well-thought out policies, mature institutions, responsible governance); and the ultimate objective of these smart cities is to facilitate and enhance human welfare and social flourishing. Researchers have shown that various technological business models and features can in fact contribute to social problems such as extremism, polarization, misinformation, and Internet addiction. In the light of these observations, addressing the philosophical and ethical questions involved in ensuring the security, safety, and interpretability of such AI algorithms that will form the technological bedrock of future cities assumes paramount importance. Globally there are calls for technology to be made more humane and human-centered. In this paper, we analyze and explore key challenges including security, robustness, interpretability, and ethical (data and algorithmic) challenges to a successful deployment of AI in human-centric applications, with a particular emphasis on the convergence of these concepts/challenges. We provide a detailed review of existing literature on these key challenges and analyze how one of these challenges may lead to others or help in solving other challenges. The paper also advises on the current limitations, pitfalls, and future directions of research in these domains, and how it can fill the current gaps and lead to better solutions. We believe such rigorous analysis will provide a baseline for future research in the domain.

Khansa Rasheed, Junaid Qadir, Terence J. O'Brien et al.

Prediction of seizure before they occur is vital for bringing normalcy to the lives of patients. Researchers employed machine learning methods using hand-crafted features for seizure prediction. However, ML methods are too complicated to select the best ML model or best features. Deep Learning methods are beneficial in the sense of automatic feature extraction. One of the roadblocks for accurate seizure prediction is scarcity of epileptic seizure data. This paper addresses this problem by proposing a deep convolutional generative adversarial network to generate synthetic EEG samples. We use two methods to validate synthesized data namely, one-class SVM and a new proposal which we refer to as convolutional epileptic seizure predictor (CESP). Another objective of our study is to evaluate performance of well-known deep learning models (e.g., VGG16, VGG19, ResNet50, and Inceptionv3) by training models on augmented data using transfer learning with average time of 10 min between true prediction and seizure onset. Our results show that CESP model achieves sensitivity of 78.11% and 88.21%, and FPR of 0.27/h and 0.14/h for training on synthesized and testing on real Epilepsyecosystem and CHB-MIT datasets, respectively. Effective results of CESP trained on synthesized data shows that synthetic data acquired the correlation between features and labels very well. We also show that employment of idea of transfer learning and data augmentation in patient-specific manner provides highest accuracy with sensitivity of 90.03% and 0.03 FPR/h which was achieved using Inceptionv3, and that augmenting data with samples generated from DCGAN increased prediction results of our CESP model and Inceptionv3 by 4-5% as compared to state-of-the-art traditional augmentation techniques. Finally, we note that prediction results of CESP achieved by using augmented data are better than chance level for both datasets.

Ihab Mohammed, Shadha Tabatabai, Ala Al-Fuqaha et al.

Machine Learning (ML), and Deep Learning (DL) in particular, play a vital role in providing smart services to the industry. These techniques however suffer from privacy and security concerns since data is collected from clients and then stored and processed at a central location. Federated Learning (FL), an architecture in which model parameters are exchanged instead of client data, has been proposed as a solution to these concerns. Nevertheless, FL trains a global model by communicating with clients over communication rounds, which introduces more traffic on the network and increases the convergence time to the target accuracy. In this work, we solve the problem of optimizing accuracy in stateful FL with a budgeted number of candidate clients by selecting the best candidate clients in terms of test accuracy to participate in the training process. Next, we propose an online stateful FL heuristic to find the best candidate clients. Additionally, we propose an IoT client alarm application that utilizes the proposed heuristic in training a stateful FL global model based on IoT device type classification to alert clients about unauthorized IoT devices in their environment. To test the efficiency of the proposed online heuristic, we conduct several experiments using a real dataset and compare the results against state-of-the-art algorithms. Our results indicate that the proposed heuristic outperforms the online random algorithm with up to 27% gain in accuracy. Additionally, the performance of the proposed online heuristic is comparable to the performance of the best offline algorithm.

Basheer Qolomany, Kashif Ahmad, Ala Al-Fuqaha et al.

Most of the research on Federated Learning (FL) has focused on analyzing global optimization, privacy, and communication, with limited attention focusing on analyzing the critical matter of performing efficient local training and inference at the edge devices. One of the main challenges for successful and efficient training and inference on edge devices is the careful selection of parameters to build local Machine Learning (ML) models. To this aim, we propose a Particle Swarm Optimization (PSO)-based technique to optimize the hyperparameter settings for the local ML models in an FL environment. We evaluate the performance of our proposed technique using two case studies. First, we consider smart city services and use an experimental transportation dataset for traffic prediction as a proxy for this setting. Second, we consider Industrial IoT (IIoT) services and use the real-time telemetry dataset to predict the probability that a machine will fail shortly due to component failures. Our experiments indicate that PSO provides an efficient approach for tuning the hyperparameters of deep Long short-term memory (LSTM) models when compared to the grid search method. Our experiments illustrate that the number of clients-server communication rounds to explore the landscape of configurations to find the near-optimal parameters are greatly reduced (roughly by two orders of magnitude needing only 2%--4% of the rounds compared to state of the art non-PSO-based approaches). We also demonstrate that utilizing the proposed PSO-based technique to find the near-optimal configurations for FL and centralized learning models does not adversely affect the accuracy of the models.

Muhammad Usama, Rupendra Nath Mitra, Inaam Ilahi et al.

Spurred by the recent advances in deep learning to harness rich information hidden in large volumes of data and to tackle problems that are hard to model/solve (e.g., resource allocation problems), there is currently tremendous excitement in the mobile networks domain around the transformative potential of data-driven AI/ML based network automation, control and analytics for 5G and beyond. In this article, we present a cautionary perspective on the use of AI/ML in the 5G context by highlighting the adversarial dimension spanning multiple types of ML (supervised/unsupervised/RL) and support this through three case studies. We also discuss approaches to mitigate this adversarial ML risk, offer guidelines for evaluating the robustness of ML models, and call attention to issues surrounding ML oriented research in 5G more generally.

Basheer Qolomany, Ihab Mohammed, Ala Al-Fuqaha et al.

With Machine Learning (ML) services now used in a number of mission-critical human-facing domains, ensuring the integrity and trustworthiness of ML models becomes all-important. In this work, we consider the paradigm where cloud service providers collect big data from resource-constrained devices for building ML-based prediction models that are then sent back to be run locally on the intermittently-connected resource-constrained devices. Our proposed solution comprises an intelligent polynomial-time heuristic that maximizes the level of trust of ML models by selecting and switching between a subset of the ML models from a superset of models in order to maximize the trustworthiness while respecting the given reconfiguration budget/rate and reducing the cloud communication overhead. We evaluate the performance of our proposed heuristic using two case studies. First, we consider Industrial IoT (IIoT) services, and as a proxy for this setting, we use the turbofan engine degradation simulation dataset to predict the remaining useful life of an engine. Our results in this setting show that the trust level of the selected models is 0.49% to 3.17% less compared to the results obtained using Integer Linear Programming (ILP). Second, we consider Smart Cities services, and as a proxy of this setting, we use an experimental transportation dataset to predict the number of cars. Our results show that the selected model's trust level is 0.7% to 2.53% less compared to the results obtained using ILP. We also show that our proposed heuristic achieves an optimal competitive ratio in a polynomial-time approximation scheme for the problem.

Ghezlane Halhoul Merabet, Mohamed Essaaidi, Mohamed Ben-Haddou et al.

Different factors such as thermal comfort, humidity, air quality, and noise have significant combined effects on the acceptability and quality of the activities performed by the building occupants who spend most of their times indoors. Among the factors cited, thermal comfort, which contributes to the human well-being because of its connection with the thermoregulation of the human body. Therefore, the creation of thermally comfortable and energy efficient environments is of great importance in the design of the buildings and hence the heating, ventilation and air-conditioning systems. Recent works have been directed towards more advanced control strategies, based mainly on artificial intelligence which has the ability to imitate human behavior. This systematic literature review aims to provide an overview of the intelligent control strategies inside building and to investigate their ability to balance thermal comfort and energy efficiency optimization in indoor environments. Methods. A systematic literature review examined the peer-reviewed research works using ACM Digital Library, Scopus, Google Scholar, IEEE Xplore (IEOL), Web of Science, and Science Direct (SDOL), besides other sources from manual search. With the following string terms: thermal comfort, comfort temperature, preferred temperature, intelligent control, advanced control, artificial intelligence, computational intelligence, building, indoors, and built environment. Inclusion criteria were: English, studies monitoring, mainly, human thermal comfort in buildings and energy efficiency simultaneously based on control strategies using the intelligent approaches. Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines were used. Initially, 1,077 articles were yielded, and 120 ultimately met inclusion criteria and were reviewed.

Khansa Rasheed, Adnan Qayyum, Junaid Qadir et al.

With the advancement in artificial intelligence (AI) and machine learning (ML) techniques, researchers are striving towards employing these techniques for advancing clinical practice. One of the key objectives in healthcare is the early detection and prediction of disease to timely provide preventive interventions. This is especially the case for epilepsy, which is characterized by recurrent and unpredictable seizures. Patients can be relieved from the adverse consequences of epileptic seizures if it could somehow be predicted in advance. Despite decades of research, seizure prediction remains an unsolved problem. This is likely to remain at least partly because of the inadequate amount of data to resolve the problem. There have been exciting new developments in ML-based algorithms that have the potential to deliver a paradigm shift in the early and accurate prediction of epileptic seizures. Here we provide a comprehensive review of state-of-the-art ML techniques in early prediction of seizures using EEG signals. We will identify the gaps, challenges, and pitfalls in the current research and recommend future directions.

Inaam Ilahi, Muhammad Usama, Junaid Qadir et al.

Deep Reinforcement Learning (DRL) has numerous applications in the real world thanks to its outstanding ability in quickly adapting to the surrounding environments. Despite its great advantages, DRL is susceptible to adversarial attacks, which precludes its use in real-life critical systems and applications (e.g., smart grids, traffic controls, and autonomous vehicles) unless its vulnerabilities are addressed and mitigated. Thus, this paper provides a comprehensive survey that discusses emerging attacks in DRL-based systems and the potential countermeasures to defend against these attacks. We first cover some fundamental backgrounds about DRL and present emerging adversarial attacks on machine learning techniques. We then investigate more details of the vulnerabilities that the adversary can exploit to attack DRL along with the state-of-the-art countermeasures to prevent such attacks. Finally, we highlight open issues and research challenges for developing solutions to deal with attacks for DRL-based intelligent systems.