Koorosh Aslansefat

Al-Harith Farhad, Ioannis Sorokos, Andreas Schmidt et al.

Machine Learning~(ML) has provided promising results in recent years across different applications and domains. However, in many cases, qualities such as reliability or even safety need to be ensured. To this end, one important aspect is to determine whether or not ML components are deployed in situations that are appropriate for their application scope. For components whose environments are open and variable, for instance those found in autonomous vehicles, it is therefore important to monitor their operational situation to determine its distance from the ML components' trained scope. If that distance is deemed too great, the application may choose to consider the ML component outcome unreliable and switch to alternatives, e.g. using human operator input instead. SafeML is a model-agnostic approach for performing such monitoring, using distance measures based on statistical testing of the training and operational datasets. Limitations in setting SafeML up properly include the lack of a systematic approach for determining, for a given application, how many operational samples are needed to yield reliable distance information as well as to determine an appropriate distance threshold. In this work, we address these limitations by providing a practical approach and demonstrate its use in a well known traffic sign recognition problem, and on an example using the CARLA open-source automotive simulator.

Koorosh Aslansefat, Mojgan Hashemian, Martin Walker et al.

Machine learning is currently undergoing an explosion in capability, popularity, and sophistication. However, one of the major barriers to widespread acceptance of machine learning (ML) is trustworthiness: most ML models operate as black boxes, their inner workings opaque and mysterious, and it can be difficult to trust their conclusions without understanding how those conclusions are reached. Explainability is therefore a key aspect of improving trustworthiness: the ability to better understand, interpret, and anticipate the behaviour of ML models. To this end, we propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.

Connor Walker, Callum Rothon, Koorosh Aslansefat et al.

With an increasing emphasis on driving down the costs of Operations and Maintenance (O&M) in the Offshore Wind (OSW) sector, comes the requirement to explore new methodology and applications of Deep Learning (DL) to the domain. Condition-based monitoring (CBM) has been at the forefront of recent research developing alarm-based systems and data-driven decision making. This paper provides a brief insight into the research being conducted in this area, with a specific focus on alarm sequence modelling and the associated challenges faced in its implementation. The paper proposes a novel idea to predict a set of relevant repair actions from an input sequence of alarm sequences, comparing Long Short-term Memory (LSTM) and Bidirectional LSTM (biLSTM) models. Achieving training accuracy results of up to 80.23%, and test accuracy results of up to 76.01% with biLSTM gives a strong indication to the potential benefits of the proposed approach that can be furthered in future research. The paper introduces a framework that integrates the proposed approach into O$\&$M procedures and discusses the potential benefits which include the reduction of a confusing plethora of alarms, as well as unnecessary vessel transfers to the turbines for fault diagnosis and correction.

Sohag Kabir, Koorosh Aslansefat, Prosanta Gope et al.

The offshore wind energy is increasingly becoming an attractive source of energy due to having lower environmental impact. Effective operation and maintenance that ensures the maximum availability of the energy generation process using offshore facilities and minimal production cost are two key factors to improve the competitiveness of this energy source over other traditional sources of energy. Condition monitoring systems are widely used for health management of offshore wind farms to have improved operation and maintenance. Reliability of the wind farms are increasingly being evaluated to aid in the maintenance process and thereby to improve the availability of the farms. However, much of the reliability analysis is performed offline based on statistical data. In this article, we propose a drone-assisted monitoring based method for online reliability evaluation of wind turbines. A blade system of a wind turbine is used as an illustrative example to demonstrate the proposed approach.

Mohammed Naveed Akram, Akshatha Ambekar, Ioannis Sorokos et al.

Reliability estimation of Machine Learning (ML) models is becoming a crucial subject. This is particularly the case when such \mbox{models} are deployed in safety-critical applications, as the decisions based on model predictions can result in hazardous situations. In this regard, recent research has proposed methods to achieve safe, \mbox{dependable}, and reliable ML systems. One such method consists of detecting and analyzing distributional shift, and then measuring how such systems respond to these shifts. This was proposed in earlier work in SafeML. This work focuses on the use of SafeML for time series data, and on reliability and robustness estimation of ML-forecasting methods using statistical distance measures. To this end, distance measures based on the Empirical Cumulative Distribution Function (ECDF) proposed in SafeML are explored to measure Statistical-Distance Dissimilarity (SDD) across time series. We then propose SDD-based Reliability Estimate (StaDRe) and SDD-based Robustness (StaDRo) measures. With the help of a clustering technique, the similarity between the statistical properties of data seen during training and the forecasts is identified. The proposed method is capable of providing a link between dataset SDD and Key Performance Indicators (KPIs) of the ML models.

Mostafa Anoosha, Dhavalkumar Thakker, Kuniko Paxton et al.

Privacy-preserving medical inference must balance data locality, diagnostic reliability, and deployment efficiency. This paper presents EcoFair, a simulated vertically partitioned inference framework for dermatological diagnosis in which raw image and tabular data remain local and only modality-specific embeddings are transmitted for server-side multimodal fusion. EcoFair introduces a lightweight-first routing mechanism that selectively activates a heavier image encoder when local uncertainty or metadata-derived clinical risk indicates that additional computation is warranted. The routing decision combines predictive uncertainty, a safe--danger probability gap, and a tabular neurosymbolic risk score derived from patient age and lesion localisation. Experiments on three dermatology benchmarks show that EcoFair can substantially reduce edge-side inference energy in representative model pairings while remaining competitive in classification performance. The results further indicate that selective routing can improve subgroup-sensitive malignant-case behaviour in representative settings without modifying the global training objective. These findings position EcoFair as a practical framework for privacy-preserving and energy-aware medical inference under edge deployment constraints.

Zeinab Dehghani, Rameez Raja Kureshi, Koorosh Aslansefat et al.

Artificial intelligence (AI) is increasingly being explored in health and social care to reduce administrative workload and allow staff to spend more time on patient care. This paper evaluates a voice-enabled Care Home Smart Speaker designed to support everyday activities in residential care homes, including spoken access to resident records, reminders, and scheduling tasks. A safety-focused evaluation framework is presented that examines the system end-to-end, combining Whisper-based speech recognition with retrieval-augmented generation (RAG) approaches (hybrid, sparse, and dense). Using supervised care-home trials and controlled testing, we evaluated 330 spoken transcripts across 11 care categories, including 184 reminder-containing interactions. These evaluations focus on (i) correct identification of residents and care categories, (ii) reminder recognition and extraction, and (iii) end-to-end scheduling correctness under uncertainty (including safe deferral/clarification). Given the safety-critical nature of care homes, particular attention is also paid to reliability in noisy environments and across diverse accents, supported by confidence scoring, clarification prompts, and human-in-the-loop oversight. In the best-performing configuration (GPT-5.2), resident ID and care category matching reached 100% (95% CI: 98.86-100), while reminder recognition reached 89.09\% (95% CI: 83.81-92.80) with zero missed reminders (100% recall) but some false positives. End-to-end scheduling via calendar integration achieved 84.65% exact reminder-count agreement (95% CI: 78.00-89.56), indicating remaining edge cases in converting informal spoken instructions into actionable events. The findings suggest that voice-enabled systems, when carefully evaluated and appropriately safeguarded, can support accurate documentation, effective task management, and trustworthy use of AI in care home settings.

Parvin Ghaffarzadeh, Debarati Chakraborty, Koorosh Aslansefat et al.

This Data Descriptor presents a fully open, multi-modal dataset for estimating vertical ground reaction force (vGRF) from consumer-grade Apple Watch sensors with laboratory force plate ground truth. Ten healthy adults aged 26--41 years performed five activities: walking, jogging, running, heel drops, and step drops, while wearing two Apple Watches positioned at the left wrist and waist. The dataset contains 492 validated trials with time-aligned inertial measurement unit (IMU) recordings (approximately 100 Hz) and force plate vGRF (Force\_Z, 1000 Hz). The release includes raw and processed time series, trial-level metadata, quality-control flags, and machine-readable data dictionaries. Trial-level matching manifests link recordings across modalities using stable identifiers. Of the 492 validated trials, 395 are triad-complete, containing wrist, waist, and force plate data, enabling cross-sensor analyses and reproducible model evaluation. Dataset quality is characterised through a three-phase cross-sensor plausibility and consistency framework, repeatability analysis of peak vGRF (intraclass correlation coefficient 0.871--0.990), and systematic checks of force ranges and trial completeness. Monte Carlo sensitivity analysis showed that correlation-based validation metrics were robust to single-sample timing perturbations at the IMU sampling resolution. All data are released under CC BY 4.0, with analysis scripts archived alongside the dataset and mirrored on GitHub. This resource supports reproducible research in wearable biomechanics, benchmarking of machine learning models for vGRF estimation, and investigation of sensor placement effects using widely available consumer wearables.

Mostafa Anoosha, Zeinab Dehghani, Kuniko Paxton et al.

Vertical Federated Learning (VFL) offers a privacy-preserving paradigm for Edge AI scenarios like mobile health diagnostics, where sensitive multimodal data reside on distributed, resource-constrained devices. Yet, standard VFL systems often suffer performance limitations due to simplistic feature fusion. This paper introduces HybridVFL, a novel framework designed to overcome this bottleneck by employing client-side feature disentanglement paired with a server-side cross-modal transformer for context-aware fusion. Through systematic evaluation on the multimodal HAM10000 skin lesion dataset, we demonstrate that HybridVFL significantly outperforms standard federated baselines, validating the criticality of advanced fusion mechanisms in robust, privacy-preserving systems.

Kuniko Paxton, Zeinab Dehghani, Koorosh Aslansefat et al.

Skin color has historically been a focal point of discrimination, yet fairness research in machine learning for medical imaging often relies on coarse subgroup categories, overlooking individual-level variations. Such group-based approaches risk obscuring biases faced by outliers within subgroups. This study introduces a distribution-based framework for evaluating and mitigating individual fairness in skin lesion classification. We treat skin tone as a continuous attribute rather than a categorical label, and employ kernel density estimation (KDE) to model its distribution. We further compare twelve statistical distance metrics to quantify disparities between skin tone distributions and propose a distance-based reweighting (DRW) loss function to correct underrepresentation in minority tones. Experiments across CNN and Transformer models demonstrate: (i) the limitations of categorical reweighting in capturing individual-level disparities, and (ii) the superior performance of distribution-based reweighting, particularly with Fidelity Similarity (FS), Wasserstein Distance (WD), Hellinger Metric (HM), and Harmonic Mean Similarity (HS). These findings establish a robust methodology for advancing fairness at individual level in dermatological AI systems, and highlight broader implications for sensitive continuous attributes in medical image analysis.

Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker et al.

In recent years, high-performance computer vision models have achieved remarkable success in medical imaging, with some skin lesion classification systems even surpassing dermatology specialists in diagnostic accuracy. However, such models are computationally intensive and large in size, making them unsuitable for deployment on edge devices. In addition, strict privacy constraints hinder centralized data management, motivating the adoption of Federated Learning (FL). To address these challenges, this study proposes a skewness-guided pruning method that selectively prunes the Multi-Head Self-Attention and Multi-Layer Perceptron layers of a multimodal Swin Transformer based on the statistical skewness of their output distributions. The proposed method was validated in a horizontal FL environment and shown to maintain performance while substantially reducing model complexity. Experiments on the compact Swin Transformer demonstrate approximately 36\% model size reduction with no loss in accuracy. These findings highlight the feasibility of achieving efficient model compression and privacy-preserving distributed learning for multimodal medical AI on edge devices.

Koorosh Aslansefat, Ioannis Sorokos, Declan Whiting et al.

Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML.

Aliasghar Arab, Milad Khaleghi, Koorosh Aslansefat

This paper presents a systematic verification and validation (V\&V) framework for the Evasive Minimum Risk Maneuver (EMRM) feature in autonomous vehicles, addressing a critical gap in existing safety assessment methods. We introduce the first formally integrated pipeline that unifies Hazard Analysis and Risk Assessment (HARA), System-Theoretic Process Analysis (STPA), and Finite State Machine (FSM) modeling into a single traceable workflow specifically designed for EMRM V\&V. HARA and STPA are combined through a structured hazard-loss mapping to identify hazards and unsafe control actions; an FSM layer captures hazard-to-loss state transitions that neither method models individually; and the unified framework drives automated scenario generation with measurable parameter-space coverage. Applied to a T-junction EMRM case study, the framework guides 1{,}880 RRT-based simulations spanning ego speed, time-to-collision (TTC), and road friction, uncovering a key physical result: the T-junction geometry gives nearly equal difficulty to stopping and to navigating, so the intermediate mitigation mode occupies only 1.9\% of the feasible parameter space. EMRM steering strategies achieve 81\% collision-avoidance rate and reduce mean residual impact speed from 18.9~km/h to 9.0~km/h compared with emergency braking alone, while the framework attains 100\% hazard, UCA, and parameter-space coverage versus $\leq$1\% for traditional methods. These results demonstrate that the integrated HARA-STPA-FSM framework enables high-resolution, traceable EMRM V\&V that is not achievable with any single method in isolation.

Seyed Mohammad Ahmadi, Koorosh Aslansefat, Ruben Valcarce-Dineiro et al.

In today's world, the significance of explainable AI (XAI) is growing in robotics and point cloud applications, as the lack of transparency in decision-making can pose considerable safety risks, particularly in autonomous systems. As these technologies are integrated into real-world environments, ensuring that model decisions are interpretable and trustworthy is vital for operational reliability and safety assurance. This study explores the implementation of SMILE, a novel explainability method originally designed for deep neural networks, on point cloud-based models. SMILE builds on LIME by incorporating Empirical Cumulative Distribution Function (ECDF) statistical distances, offering enhanced robustness and interpretability, particularly when the Anderson-Darling distance is used. The approach demonstrates superior performance in terms of fidelity loss, R2 scores, and robustness across various kernel widths, perturbation numbers, and clustering configurations. Moreover, this study introduces a stability analysis for point cloud data using the Jaccard index, establishing a new benchmark and baseline for model stability in this field. The study further identifies dataset biases in the classification of the 'person' category, emphasizing the necessity for more comprehensive datasets in safety-critical applications like autonomous driving and robotics. The results underscore the potential of advanced explainability models and highlight areas for future research, including the application of alternative surrogate models and explainability techniques in point cloud data.

Zeinab Dehghani, Koorosh Aslansefat, Adil Khan et al.

Despite recent advancements in Instruct-based Image Editing models for generating high-quality images, they are known as black boxes and a significant barrier to transparency and user trust. To solve this issue, we introduce SMILE (Statistical Model-agnostic Interpretability with Local Explanations), a novel model-agnostic for localized interpretability that provides a visual heatmap to clarify the textual elements' influence on image-generating models. We applied our method to various Instruction-based Image Editing models like Pix2Pix, Image2Image-turbo and Diffusers-Inpaint and showed how our model can improve interpretability and reliability. Also, we use stability, accuracy, fidelity, and consistency metrics to evaluate our method. These findings indicate the exciting potential of model-agnostic interpretability for reliability and trustworthiness in critical applications such as healthcare and autonomous driving while encouraging additional investigation into the significance of interpretability in enhancing dependable image editing models.

Al-Harith Farhad, Ioannis Sorokos, Mohammed Naveed Akram et al.

The zeitgeist of the digital era has been dominated by an expanding integration of Artificial Intelligence~(AI) in a plethora of applications across various domains. With this expansion, however, questions of the safety and reliability of these methods come have become more relevant than ever. Consequently, a run-time ML model safety system has been developed to ensure the model's operation within the intended context, especially in applications whose environments are greatly variable such as Autonomous Vehicles~(AVs). SafeML is a model-agnostic approach for performing such monitoring, using distance measures based on statistical testing of the training and operational datasets; comparing them to a predetermined threshold, returning a binary value whether the model should be trusted in the context of the observed data or be deemed unreliable. Although a systematic framework exists for this approach, its performance is hindered by: (1) a dependency on a number of design parameters that directly affect the selection of a safety threshold and therefore likely affect its robustness, (2) an inherent assumption of certain distributions for the training and operational sets, as well as (3) a high computational complexity for relatively large sets. This work addresses these limitations by changing the binary decision to a continuous metric. Furthermore, all data distribution assumptions are made obsolete by implementing non-parametric approaches, and the computational speed increased by introducing a new distance measure based on the Empirical Characteristics Functions~(ECF).

Kuniko Paxton, Medina Kapo, Amila Akagić et al.

Skin cancer, particularly melanoma, remains a major cause of morbidity and mortality, making early detection critical. AI-driven dermatology systems often rely on skin lesion segmentation as a preprocessing step to delineate the lesion from surrounding skin and support downstream analysis. While fairness concerns regarding skin tone have been widely studied for lesion classification, the influence of skin tone on the segmentation stage remains under-quantified and is frequently assessed using coarse, discrete skin tone categories. In this work, we evaluate three strong segmentation architectures (UNet, DeepLabV3 with a ResNet50 backbone, and DINOv2) on two public dermoscopic datasets (HAM10000 and ISIC2017) and introduce a continuous pigment or contrast analysis that treats pixel-wise ITA values as distributions. Using Wasserstein distances between within-image distributions for skin-only, lesion-only, and whole-image regions, we quantify lesion skin contrast and relate it to segmentation performance across multiple metrics. Within the range represented in these datasets, global skin tone metrics (Fitzpatrick grouping or mean ITA) show weak association with segmentation quality. In contrast, low lesion-skin contrast is consistently associated with larger segmentation errors in models, indicating that boundary ambiguity and low contrast are key drivers of failure. These findings suggest that fairness improvements in dermoscopic segmentation should prioritize robust handling of low-contrast lesions, and the distribution-based pigment measures provide a more informative audit signal than discrete skin-tone categories.

Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker et al.

Fairness is a critical component of Trustworthy AI. In this paper, we focus on Machine Learning (ML) and the performance of model predictions when dealing with skin color. Unlike other sensitive attributes, the nature of skin color differs significantly. In computer vision, skin color is represented as tensor data rather than categorical values or single numerical points. However, much of the research on fairness across sensitive groups has focused on categorical features such as gender and race. This paper introduces a new technique for evaluating fairness in ML for image classification tasks, specifically without the use of annotation. To address the limitations of prior work, we handle tensor data, like skin color, without classifying it rigidly. Instead, we convert it into probability distributions and apply statistical distance measures. This novel approach allows us to capture fine-grained nuances in fairness both within and across what would traditionally be considered distinct groups. Additionally, we propose an innovative training method to mitigate the latent biases present in conventional skin tone categorization. This method leverages color distance estimates calculated through Bayesian regression with polynomial functions, ensuring a more nuanced and equitable treatment of skin color in ML models.

Zeinab Dehghani, Mohammed Naveed Akram, Koorosh Aslansefat et al.

Large Language Models (LLMs) such as GPT, LLaMA, and Claude achieve remarkable performance in text generation but remain opaque in their decision-making processes, limiting trust and accountability in high-stakes applications. We present gSMILE (generative SMILE), a model-agnostic, perturbation-based framework for token-level interpretability in LLMs. Extending the SMILE methodology, gSMILE uses controlled prompt perturbations, Wasserstein distance metrics, and weighted linear surrogates to identify input tokens with the most significant impact on the output. This process enables the generation of intuitive heatmaps that visually highlight influential tokens and reasoning paths. We evaluate gSMILE across leading LLMs (OpenAI's gpt-3.5-turbo-instruct, Meta's LLaMA 3.1 Instruct Turbo, and Anthropic's Claude 2.1) using attribution fidelity, attribution consistency, attribution stability, attribution faithfulness, and attribution accuracy as metrics. Results show that gSMILE delivers reliable human-aligned attributions, with Claude 2.1 excelling in attention fidelity and GPT-3.5 achieving the highest output consistency. These findings demonstrate gSMILE's ability to balance model performance and interpretability, enabling more transparent and trustworthy AI systems.

Oliver Dunn, Koorosh Aslansefat, Yiannis Papadopoulos

The rise of machine learning in safety-critical systems has paralleled advancements in quantum computing, leading to the emerging field of Quantum Machine Learning (QML). While safety monitoring has progressed in classical ML, existing methods are not directly applicable to QML due to fundamental differences in quantum computation. Given the novelty of QML, dedicated safety mechanisms remain underdeveloped. This paper introduces Q-SafeML, a safety monitoring approach for QML. The method builds on SafeML, a recent method that utilizes statistical distance measures to assess model accuracy and provide confidence in the reasoning of an algorithm. An adapted version of Q-SafeML incorporates quantum-centric distance measures, aligning with the probabilistic nature of QML outputs. This shift to a model-dependent, post-classification evaluation represents a key departure from classical SafeML, which is dataset-driven and classifier-agnostic. The distinction is motivated by the unique representational constraints of quantum systems, requiring distance metrics defined over quantum state spaces. Q-SafeML detects distances between operational and training data addressing the concept drifts in the context of QML. Experiments on QCNN and VQC Models show that this enables informed human oversight, enhancing system transparency and safety.

Connor Walker, Koorosh Aslansefat, Mohammad Naveed Akram et al.

Accuracy and safety are paramount in Offshore Wind (OSW) maintenance, yet conventional Large Language Models (LLMs) often fail when confronted with highly specialised or unexpected scenarios. We introduce RAGuard, an enhanced Retrieval-Augmented Generation (RAG) framework that explicitly integrates safety-critical documents alongside technical manuals.By issuing parallel queries to two indices and allocating separate retrieval budgets for knowledge and safety, RAGuard guarantees both technical depth and safety coverage. We further develop a SafetyClamp extension that fetches a larger candidate pool, "hard-clamping" exact slot guarantees to safety. We evaluate across sparse (BM25), dense (Dense Passage Retrieval) and hybrid retrieval paradigms, measuring Technical Recall@K and Safety Recall@K. Both proposed extensions of RAG show an increase in Safety Recall@K from almost 0\% in RAG to more than 50\% in RAGuard, while maintaining Technical Recall above 60\%. These results demonstrate that RAGuard and SafetyClamp have the potential to establish a new standard for integrating safety assurance into LLM-powered decision support in critical maintenance contexts.

Zahra Zehtabi Sabeti Moghaddam, Zeinab Dehghani, Maneeha Rani et al.

Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves accuracy by grounding outputs in external knowledge, especially in domains like healthcare, where precision is vital. However, RAG remains opaque and essentially a black box, heavily dependent on data quality. We developed a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE and named it as Knowledge-Graph (KG)-SMILE. By applying controlled perturbations, computing similarities, and training weighted linear surrogates, KG-SMILE identifies the graph entities and relations most influential to generated outputs, thereby making RAG more transparent. We evaluate KG-SMILE using comprehensive attribution metrics, including fidelity, faithfulness, consistency, stability, and accuracy. Our findings show that KG-SMILE produces stable, human-aligned explanations, demonstrating its capacity to balance model effectiveness with interpretability and thereby fostering greater transparency and trust in machine learning technologies.

Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker et al.

Recent advances in deep learning have significantly improved the accuracy of skin lesion classification models, supporting medical diagnoses and promoting equitable healthcare. However, concerns remain about potential biases related to skin color, which can impact diagnostic outcomes. Ensuring fairness is challenging due to difficulties in classifying skin tones, high computational demands, and the complexity of objectively verifying fairness. To address these challenges, we propose a fairness algorithm for skin lesion classification that overcomes the challenges associated with achieving diagnostic fairness across varying skin tones. By calculating the skewness of the feature map in the convolution layer of the VGG (Visual Geometry Group) network and the patches and the heads of the Vision Transformer, our method reduces unnecessary channels related to skin tone, focusing instead on the lesion area. This approach lowers computational costs and mitigates bias without relying on conventional statistical methods. It potentially reduces model size while maintaining fairness, making it more practical for real-world applications.

Kuniko Paxton, Koorosh Aslansefat, Amila Akagić et al.

Recent advancements in skin lesion classification models have significantly improved accuracy, with some models even surpassing dermatologists' diagnostic performance. However, in medical practice, distrust in AI models remains a challenge. Beyond high accuracy, trustworthy, explainable diagnoses are essential. Existing explainability methods have reliability issues, with LIME-based methods suffering from inconsistency, while CAM-based methods failing to consider all classes. To address these limitations, we propose Global Class Activation Probabilistic Map Evaluation, a method that analyses all classes' activation probability maps probabilistically and at a pixel level. By visualizing the diagnostic process in a unified manner, it helps reduce the risk of misdiagnosis. Furthermore, the application of SafeML enhances the detection of false diagnoses and issues warnings to doctors and patients as needed, improving diagnostic reliability and ultimately patient safety. We evaluated our method using the ISIC datasets with MobileNetV2 and Vision Transformers.