Vishal Sharma

Min Shi, Anagha Lokhande, Mojtaba S. Fazli et al. · harvard, stanford

Ophthalmic images and derivatives such as the retinal nerve fiber layer (RNFL) thickness map are crucial for detecting and monitoring ophthalmic diseases (e.g., glaucoma). For computer-aided diagnosis of eye diseases, the key technique is to automatically extract meaningful features from ophthalmic images that can reveal the biomarkers (e.g., RNFL thinning patterns) linked to functional vision loss. However, representation learning from ophthalmic images that links structural retinal damage with human vision loss is non-trivial mostly due to large anatomical variations between patients. The task becomes even more challenging in the presence of image artifacts, which are common due to issues with image acquisition and automated segmentation. In this paper, we propose an artifact-tolerant unsupervised learning framework termed EyeLearn for learning representations of ophthalmic images. EyeLearn has an artifact correction module to learn representations that can best predict artifact-free ophthalmic images. In addition, EyeLearn adopts a clustering-guided contrastive learning strategy to explicitly capture the intra- and inter-image affinities. During training, images are dynamically organized in clusters to form contrastive samples in which images in the same or different clusters are encouraged to learn similar or dissimilar representations, respectively. To evaluate EyeLearn, we use the learned representations for visual field prediction and glaucoma detection using a real-world ophthalmic image dataset of glaucoma patients. Extensive experiments and comparisons with state-of-the-art methods verified the effectiveness of EyeLearn for learning optimal feature representations from ophthalmic images.

Paul Brookes, Vardan Voskanyan, Rafail Giavrimis et al.

Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software development to customer support. However, LLM agents often underperform due to suboptimal configurations; poorly tuned prompts, tool descriptions, and parameters that typically require weeks of manual refinement. Existing optimization methods either are too complex for general use or treat components in isolation, missing critical interdependencies. We present ARTEMIS, a no-code evolutionary optimization platform that jointly optimizes agent configurations through semantically-aware genetic operators. Given only a benchmark script and natural language goals, ARTEMIS automatically discovers configurable components, extracts performance signals from execution logs, and evolves configurations without requiring architectural modifications. We evaluate ARTEMIS on four representative agent systems: the \emph{ALE Agent} for competitive programming on AtCoder Heuristic Contest, achieving a \textbf{$13.6\%$ improvement} in acceptance rate; the \emph{Mini-SWE Agent} for code optimization on SWE-Perf, with a statistically significant \textbf{10.1\% performance gain}; and the \emph{CrewAI Agent} for cost and mathematical reasoning on Math Odyssey, achieving a statistically significant \textbf{$36.9\%$ reduction} in the number of tokens required for evaluation. We also evaluate the \emph{MathTales-Teacher Agent} powered by a smaller open-source model (Qwen2.5-7B) on GSM8K primary-level mathematics problems, achieving a \textbf{22\% accuracy improvement} and demonstrating that ARTEMIS can optimize agents based on both commercial and local models.

Pankaj Gupta, Priya Mudgil, Niharika Dutta et al.

Background: Pancreatic cancer is one of the most aggressive cancers, with poor survival rates. Endoscopic ultrasound (EUS) is a key diagnostic modality, but its effectiveness is constrained by operator subjectivity. This study evaluates a Vision Transformer-based deep learning segmentation model for pancreatic tumors. Methods: A segmentation model using the USFM framework with a Vision Transformer backbone was trained and validated with 17,367 EUS images (from two public datasets) in 5-fold cross-validation. The model was tested on an independent dataset of 350 EUS images from another public dataset, manually segmented by radiologists. Preprocessing included grayscale conversion, cropping, and resizing to 512x512 pixels. Metrics included Dice similarity coefficient (DSC), intersection over union (IoU), sensitivity, specificity, and accuracy. Results: In 5-fold cross-validation, the model achieved a mean DSC of 0.651 +/- 0.738, IoU of 0.579 +/- 0.658, sensitivity of 69.8%, specificity of 98.8%, and accuracy of 97.5%. For the external validation set, the model achieved a DSC of 0.657 (95% CI: 0.634-0.769), IoU of 0.614 (95% CI: 0.590-0.689), sensitivity of 71.8%, and specificity of 97.7%. Results were consistent, but 9.7% of cases exhibited erroneous multiple predictions. Conclusions: The Vision Transformer-based model demonstrated strong performance for pancreatic tumor segmentation in EUS images. However, dataset heterogeneity and limited external validation highlight the need for further refinement, standardization, and prospective studies.

Sanket Gandhi, Atul, Samanyu Mahajan et al.

Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can learning disentangled representation further improve the accuracy of visual dynamics prediction in object-centric models?" While there has been some attempt to learn such disentangled representations for the case of static images \citep{nsb}, to the best of our knowledge, ours is the first work which tries to do this in a general setting for video, without making any specific assumptions about the kind of attributes that an object might have. The key building block of our architecture is the notion of a {\em block}, where several blocks together constitute an object. Each block is represented as a linear combination of a given number of learnable concept vectors, which is iteratively refined during the learning process. The blocks in our model are discovered in an unsupervised manner, by attending over object masks, in a style similar to discovery of slots \citep{slot_attention}, for learning a dense object-centric representation. We employ self-attention via transformers over the discovered blocks to predict the next state resulting in discovery of visual dynamics. We perform a series of experiments on several benchmark 2-D, and 3-D datasets demonstrating that our architecture (1) can discover semantically meaningful blocks (2) help improve accuracy of dynamics prediction compared to SOTA object-centric models (3) perform significantly better in OOD setting where the specific attribute combinations are not seen earlier during training. Our experiments highlight the importance discovery of disentangled representation for visual dynamics prediction.

Vishal Sharma, Curtis Dyreson

Coronavirus Disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 virus (SARS-CoV-2). The virus transmits rapidly; it has a basic reproductive number R of 2.2-2.7. In March 2020, the World Health Organization declared the COVID-19 outbreak a pandemic. COVID-19 is currently affecting more than 200 countries with 6M active cases. An effective testing strategy for COVID-19 is crucial to controlling the outbreak but the demand for testing surpasses the availability of test kits that use Reverse Transcription Polymerase Chain Reaction (RT-PCR). In this paper, we present a technique to screen for COVID-19 using artificial intelligence. Our technique takes only seconds to screen for the presence of the virus in a patient. We collected a dataset of chest X-ray images and trained several popular deep convolution neural network-based models (VGG, MobileNet, Xception, DenseNet, InceptionResNet) to classify the chest X-rays. Unsatisfied with these models, we then designed and built a Residual Attention Network that was able to screen COVID-19 with a testing accuracy of 98% and a validation accuracy of 100%. A feature maps visual of our model show areas in a chest X-ray which are important for classification. Our work can help to increase the adaptation of AI-assisted applications in clinical practice. The code and dataset used in this project are available at https://github.com/vishalshar/covid-19-screening-using-RAN-on-X-ray-images.

Vishal Sharma, Zekun Zhang, Zachary Neubert et al.

Speaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channel). We train Neural Network for learning when a person is speaking. We use different type of Neural Networks specifically, Single Layer Perceptron (SLP), Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN) and Convolution Neural Network (CNN) we achieve $\sim$92\% of accuracy with RNN. The code for this project is available at https://github.com/vishalshar/SpeakerDiarization_RNN_CNN_LSTM

Pranoy Panda, Raghav Magazine, Chaitanya Devaguptapu et al.

Large Language Models (LLMs) have revolutionized natural language processing, but their varying capabilities and costs pose challenges in practical applications. LLM routing addresses this by dynamically selecting the most suitable LLM for each query/task. Previous approaches treat this as a supervised learning problem, assuming complete knowledge of optimal query-LLM pairings. However, real-world scenarios lack such comprehensive mappings and face evolving user queries. We thus propose to study LLM routing as a contextual bandit problem, enabling adaptive decision-making using bandit feedback without requiring exhaustive inference across all LLMs for all queries (in contrast to supervised routing). To address this problem, we develop a shared embedding space for queries and LLMs, where query and LLM embeddings are aligned to reflect their affinity. This space is initially learned from offline human preference data and refined through online bandit feedback. We instantiate this idea through Preference-prior Informed Linucb fOr adaptive rouTing (PILOT), a novel extension of LinUCB. To handle diverse user budgets for model routing, we introduce an online cost policy modeled as a multi-choice knapsack problem, ensuring resource-efficient routing.

Abdullah Abdullah, Fannya Ratana Sandjaja, Ayesha Abdul Majeed et al.

This study investigates uncertainty quantification (UQ) using quantum-classical hybrid machine learning (ML) models for applications in complex and dynamic fields, such as attaining resiliency in supply chain digital twins and financial risk assessment. Although quantum feature transformations have been integrated into ML models for complex data tasks, a gap exists in determining their impact on UQ within their hybrid architectures (quantum-classical approach). This work applies existing UQ techniques for different models within a hybrid framework, examining how quantum feature transformation affects uncertainty propagation. Increasing qubits from 4 to 16 shows varied model responsiveness to outlier detection (OD) samples, which is a critical factor for resilient decision-making in dynamic environments. This work shows how quantum computing techniques can transform data features for UQ, particularly when combined with classical methods.

Mohit Meena, Yash Punjabi, Abhishek A et al.

Graph Neural Networks (GNNs) have emerged as powerful tools for learning over graph-structured data, yet recent studies have shown that their performance gains are beginning to plateau. In many cases, well-established models such as GCN and GAT, when appropriately tuned, can match or even exceed the performance of more complex, state-of-the-art architectures. This trend highlights a key limitation in the current landscape: the difficulty of selecting the most suitable model for a given graph task or dataset. To address this, we propose Self-Adaptive Graph Mixture of Models (SAGMM), a modular and practical framework that learns to automatically select and combine the most appropriate GNN models from a diverse pool of architectures. Unlike prior mixture-of-experts approaches that rely on variations of a single base model, SAGMM leverages architectural diversity and a topology-aware attention gating mechanism to adaptively assign experts to each node based on the structure of the input graph. To improve efficiency, SAGMM includes a pruning mechanism that reduces the number of active experts during training and inference without compromising performance. We also explore a training-efficient variant in which expert models are pretrained and frozen, and only the gating and task-specific layers are trained. We evaluate SAGMM on 16 benchmark datasets covering node classification, graph classification, regression, and link prediction tasks, and demonstrate that it consistently outperforms or matches leading GNN baselines and prior mixture-based methods, offering a robust and adaptive solution for real-world graph learning.

Md Abul Bashar, Richi Nayak, Anjor Kothare et al.

To create a more inclusive workplace, enterprises are actively investing in identifying and eliminating unconscious bias (e.g., gender, race, age, disability, elitism and religion) across their various functions. We propose a deep learning model with a transfer learning based language model to learn from manually tagged documents for automatically identifying bias in enterprise content. We first pretrain a deep learning-based language-model using Wikipedia, then fine tune the model with a large unlabelled data set related with various types of enterprise content. Finally, a linear layer followed by softmax layer is added at the end of the language model and the model is trained on a labelled bias dataset consisting of enterprise content. The trained model is thoroughly evaluated on independent datasets to ensure a general application. We present the proposed method and its deployment detail in a real-world application.

Vishal Sharma, Zengpeng Li, Pawel Szalachowski et al.

Decentralized control, low-complexity, flexible and efficient communications are the requirements of an architecture that aims to scale blockchains beyond the current state. Such properties are attainable by reducing ledger size and providing parallel operations in the blockchain. Sharding is one of the approaches that lower the burden of the nodes and enhance performance. However, the current solutions lack the features for resolving concurrency during cross-shard communications. With multiple participants belonging to different shards, handling concurrent operations is essential for optimal sharding. This issue becomes prominent due to the lack of architectural support and requires additional consensus for cross-shard communications. Inspired by hybrid Proof-of-Work/Proof-of-Stake (PoW/PoS), like Ethereum, hybrid consensus and 2-hop blockchain, we propose Reinshard, a new blockchain that inherits the properties of hybrid consensus for optimal sharding. Reinshard uses PoW and PoS chain-pairs with PoS sub-chains for all the valid chain-pairs where the hybrid consensus is attained through Verifiable Delay Function (VDF). Our architecture provides a secure method of arranging nodes in shards and resolves concurrency conflicts using the delay factor of VDF. The applicability of Reinshard is demonstrated through security and experimental evaluations. A practical concurrency problem is considered to show the efficacy of Reinshard in providing optimal sharding.

Zengpeng Li, Teik Guan Tan, Pawel Szalachowski et al.

A verifiable random function (VRF in short) is a powerful pseudo-random function that provides a non-interactively public verifiable proof for the correctness of its output. Recently, VRFs have found essential applications in blockchain design, such as random beacons and proof-of-stake consensus protocols. To our knowledge, the first generation of blockchain systems used inherently inefficient proof-of-work consensuses, and the research community tried to achieve the same properties by proposing proof-of-stake schemes where resource-intensive proof-of-work is emulated by cryptographic constructions. Unfortunately, those most discussed proof-of-stake consensuses (e.g., Algorand and Ouroborous family) are not future-proof because the building blocks are secure only under the classical hard assumptions; in particular, their designs ignore the advent of quantum computing and its implications. In this paper, we propose a generic compiler to obtain the post-quantum VRF from the simple VRF solution using symmetric-key primitives (e.g., non-interactive zero-knowledge system) with an intrinsic property of quantum-secure. Our novel solution is realized via two efficient zero-knowledge systems ZKBoo and ZKB++, respectively, to validate the compiler correctness. Our proof-of-concept implementation indicates that even today, the overheads introduced by our solution are acceptable in real-world deployments. We also demonstrate potential applications of a quantum-secure VRF, such as quantum-secure decentralized random beacon and lottery-based proof of stake consensus blockchain protocol.

Rushil Gupta, Vishal Sharma, Yash Jain et al.

We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object representations, and propagate a loss in the latent space. Specifically, our research builds on recent work by Kipf et al. \cite{kipf&al20}, which predicts the next state via contrastive learning of object interactions in a latent space using a Graph Neural Network. We argue that injecting explicit inductive bias in the model, in form of general physical laws, can help not only make the model more interpretable, but also improve the overall prediction of model. As a natural by-product, our model can learn feature maps which closely resemble actual object positions in the image, without having any explicit supervision about the object positions at the training time. In comparison with earlier works \cite{jaques&al20}, which assume a complete knowledge of the dynamics governing the motion in the form of a physics engine, we rely only on the knowledge of general physical laws, such as, world consists of objects, which have position and velocity. We propose an additional decoder based loss in the pixel space, imposed in a curriculum manner, to further refine the latent space predictions. Experiments in multiple different settings demonstrate that while Kipf et al. model is effective at capturing object interactions, our model can be significantly more effective at localising objects, resulting in improved performance in 3 out of 4 domains that we experiment with. Additionally, our model can learn highly intrepretable feature maps, resembling actual object positions.

Gaurav Choudhary, Vishal Sharma

The 5G networks have the capability to provide high compatibility for the new applications, industries, and business models. These networks can tremendously improve the quality of life by enabling various use cases that require high data-rate, low latency, and continuous connectivity for applications pertaining to eHealth, automatic vehicles, smart cities, smart grid, and the Internet of Things (IoT). However, these applications need secure servicing as well as resource policing for effective network formations. There have been a lot of studies, which emphasized the security aspects of 5G networks while focusing only on the adaptability features of these networks. However, there is a gap in the literature which particularly needs to follow recent computing paradigms as alternative mechanisms for the enhancement of security. To cover this, a detailed description of the security for the 5G networks is presented in this article along with the discussions on the evolution of osmotic and catalytic computing-based security modules. The taxonomy on the basis of security requirements is presented, which also includes the comparison of the existing state-of-the-art solutions. This article also provides a security model, "CATMOSIS", which idealizes the incorporation of security features on the basis of catalytic and osmotic computing in the 5G networks. Finally, various security challenges and open issues are discussed to emphasize the works to follow in this direction of research.

Vishal Sharma, Jiyoon Kim, Yongho Ko et al.

Cellular (C) setups facilitate the connectivity amongst the devices with better provisioning of services to its users. Vehicular networks are one of the representative setups that aim at expanding their functionalities by using the available cellular systems like Long Term Evolution (LTE)-based Evolved Universal Terrestrial Radio Access Network (E-UTRAN) as well as the upcoming Fifth Generation (5G)-based functional architecture. The vehicular networks include Vehicle to Vehicle (V2V), Vehicle to Infrastructure (V2I), Vehicle to Pedestrian (V2P) and Vehicle to Network (V2N), all of which are referred to as Vehicle to Everything (V2X). 5G has dominated the vehicular network and most of the upcoming research is motivated towards the fully functional utilization of 5G-V2X. Despite that, credential management and edge-initiated security are yet to be resolved under 5G-V2X. To further understand the issue, this paper presents security management as a principle of sustainability and key-management. The performance tradeoff is evaluated with the key-updates required to maintain a secure connection between the vehicles and the 5G-terminals. The proposed approach aims at the utilization of high-speed mmWave-based backhaul for enhancing the security operations between the core and the sub-divided functions at the edge of the network through a dual security management framework. The evaluations are conducted using numerical simulations, which help to understand the impact on the sustainability of connections as well as identification of the fail-safe points for secure and fast operations. Furthermore, the evaluations help to follow the multiple tradeoffs of security and performance based on the metrics like mandatory key updates, the range of operations and the probability of connectivity.

Gaurav Choudhary, Jiyoon Kim, Vishal Sharma

The rapid involution of the mobile generation with incipient data networking capabilities and utilization has exponentially increased the data traffic volumes. Such traffic drains various key issues in 5G mobile backhaul networks. Security of mobile backhaul is of utmost importance; however, there are a limited number of articles, which have explored such a requirement. This paper discusses the potential design issues and key challenges of the secure 5G mobile backhaul architecture. The comparisons of the existing state-of-the-art solutions for secure mobile backhaul, together with their major contributions have been explored. Furthermore, the paper discussed various key issues related to Quality of Service (QoS), routing and scheduling, resource management, capacity enhancement, latency, security-management, and handovers using mechanisms like Software Defined Networking and millimeter Wave technologies. Moreover, the trails of research challenges and future directions are additionally presented.

Vishal Sharma, Ilsun You, Nadra Guizani

Cellular-Vehicle to Everything (C-V2X) aims at resolving issues pertaining to the traditional usability of Vehicle to Infrastructure (V2I) and Vehicle to Vehicle (V2V) networking. Specifically, C-V2X lowers the number of entities involved in vehicular communications and allows the inclusion of cellular-security solutions to be applied to V2X. For this, the evolvement of LTE-V2X is revolutionary, but it fails to handle the demands of high throughput, ultra-high reliability, and ultra-low latency alongside its security mechanisms. To counter this, 5G-V2X is considered as an integral solution, which not only resolves the issues related to LTE-V2X but also provides a function-based network setup. Several reports have been given for the security of 5G, but none of them primarily focuses on the security of 5G-V2X. This article provides a detailed overview of 5G-V2X with a security-based comparison to LTE-V2X. A novel Security Reflex Function (SRF)-based architecture is proposed and several research challenges are presented related to the security of 5G-V2X. Furthermore, the article lays out requirements of Ultra-Dense and Ultra-Secure (UD-US) transmissions necessary for 5G-V2X.

Vishal Sharma, Ilsun You, Karl Andersson et al.

With an enormous range of applications, Internet of Things (IoT) has magnetized industries and academicians from everywhere. IoT facilitates operations through ubiquitous connectivity by providing Internet access to all the devices with computing capabilities. With the evolution of wireless infrastructure, the focus from simple IoT has been shifted to smart, connected and mobile IoT (M-IoT) devices and platforms, which can enable low-complexity, low-cost and efficient computing through sensors, machines, and even crowdsourcing. All these devices can be grouped under a common term of M-IoT. Even though the positive impact on applications has been tremendous, security, privacy and trust are still the major concerns for such networks and an insufficient enforcement of these requirements introduces non-negligible threats to M-IoT devices and platforms. Thus, it is important to understand the range of solutions which are available for providing a secure, privacy-compliant, and trustworthy mechanism for M-IoT. There is no direct survey available, which focuses on security, privacy, trust, secure protocols, physical layer security and handover protections in M-IoT. This paper covers such requisites and presents comparisons of state-the-art solutions for IoT which are applicable to security, privacy, and trust in smart and connected M-IoT networks. Apart from these, various challenges, applications, advantages, technologies, standards, open issues, and roadmap for security, privacy and trust are also discussed in this paper.

Vishal Sharma

The blockchain is a safe, reliable and innovative mechanism for managing numerous vehicles seeking connectivity. However, following the principles of the blockchain, the number of transactions required to update ledgers pose serious issues for vehicles as these may consume the maximum available energy. To resolve this, an efficient model is presented in this letter which is capable of handling the energy demands of the blockchain-enabled Internet of Vehicles (IoV) by optimally controlling the number of transactions through distributed clustering. Numerical results suggest that the proposed approach is 40.16% better in terms of energy conservation and 82.06% better in terms of the number of transactions required to share the entire blockchain-data compared with the traditional blockchain.

Vishal Sharma, Noman Ahmed Sheikh, Happy Mittal et al.

Lifted inference reduces the complexity of inference in relational probabilistic models by identifying groups of constants (or atoms) which behave symmetric to each other. A number of techniques have been proposed in the literature for lifting marginal as well MAP inference. We present the first application of lifting rules for marginal-MAP (MMAP), an important inference problem in models having latent (random) variables. Our main contribution is two fold: (1) we define a new equivalence class of (logical) variables, called Single Occurrence for MAX (SOM), and show that solution lies at extreme with respect to the SOM variables, i.e., predicate groundings differing only in the instantiation of the SOM variables take the same truth value (2) we define a sub-class {\em SOM-R} (SOM Reduce) and exploit properties of extreme assignments to show that MMAP inference can be performed by reducing the domain of SOM-R variables to a single constant.We refer to our lifting technique as the {\em SOM-R} rule for lifted MMAP. Combined with existing rules such as decomposer and binomial, this results in a powerful framework for lifted MMAP. Experiments on three benchmark domains show significant gains in both time and memory compared to ground inference as well as lifted approaches not using SOM-R.

Gaurav Choudhary, Vishal Sharma, Ilsun You et al.

Unmanned Aerial Vehicles (UAV)-based civilian or military applications become more critical to serving civilian and/or military missions. The significantly increased attention on UAV applications also has led to security concerns particularly in the context of networked UAVs. Networked UAVs are vulnerable to malicious attacks over open-air radio space and accordingly, intrusion detection systems (IDSs) have been naturally derived to deal with the vulnerabilities and/or attacks. In this paper, we briefly survey the state-of-the-art IDS mechanisms that deal with vulnerabilities and attacks under networked UAV environments. In particular, we classify the existing IDS mechanisms according to information gathering sources, deployment strategies, detection methods, detection states, IDS acknowledgment, and intrusion types. We conclude this paper with research challenges, insights, and future research directions to propose a networked UAV-IDS system which meets required standards of effectiveness and efficiency in terms of the goals of both security and performance.

Takshi Gupta, Gaurav Choudhary, Vishal Sharma

Pervasive Online Social Networks (POSNs) are the extensions of Online Social Networks (OSNs) which facilitate connectivity irrespective of the domain and properties of users. POSNs have been accumulated with the convergence of a plethora of social networking platforms with a motivation of bridging their gap. Over the last decade, OSNs have visually perceived an altogether tremendous amount of advancement in terms of the number of users as well as technology enablers. A single OSN is the property of an organization, which ascertains smooth functioning of its accommodations for providing a quality experience to their users. However, with POSNs, multiple OSNs have coalesced through communities, circles, or only properties, which make service-provisioning tedious and arduous to sustain. Especially, challenges become rigorous when the focus is on the security perspective of cross-platform OSNs, which are an integral part of POSNs. Thus, it is of utmost paramountcy to highlight such a requirement and understand the current situation while discussing the available state-of-the-art. With the modernization of OSNs and convergence towards POSNs, it is compulsory to understand the impact and reach of current solutions for enhancing the security of users as well as associated services. This survey understands this requisite and fixates on different sets of studies presented over the last few years and surveys them for their applicability to POSNs...

Vishal Sharma, Jiyoon Kim, Soonhyun Kwon et al.

Internet of Things (IoT) aims at providing connectivity between every computing entity. However, this facilitation is also leading to more cyber threats which may exploit the presence of a vulnerability of a period of time. One such vulnerability is the zero-day threat that may lead to zero-day attacks which are detrimental to an enterprise as well as the network security. In this article, a study is presented on the zero-day threats for IoT networks and a context graph-based framework is presented to provide a strategy for mitigating these attacks. The proposed approach uses a distributed diagnosis system for classifying the context at the central service provider as well as at the local user site. Once a potential zero-day attack is identified, a critical data sharing protocol is used to transmit alert messages and reestablish the trust between the network entities and the IoT devices. The results show that the distributed approach is capable of mitigating the zero-day threats efficiently with 33% and 21% improvements in terms of cost of operation and communication overheads, respectively, in comparison with the centralized diagnosis system.