Sudhish N. Gerorge
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sudhish N. Gerorge has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Kiran Raja
Norwegian University of Science and Technology
11 shared publications - Baburaj Madathil
Government Engineering College Kozhikode
8 shared publications - Nirmal Joseph
Department of Electronics and Communication Engineering, National Institute of Technology, Calicut, India
8 shared publications - Sony George
Department of Computer Science, NTNU - Norwegian University of Science and Technology, Gjøvik, Norway
5 shared publications - Abdu Rahiman V
Government Engineering College Kozhikode, Calicut, India
4 shared publications - Anju Jose Tom
Inria Rennes Bretagne Atlantique, Beauliau Campus, Rennes, France
4 shared publications
Latest Publications
- 18 November 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 131
Phantom attack: A novel attack for radiomics-based disease classification
- 18 November 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 131
Phantom attack: A novel attack for radiomics-based disease classification
- 3 November 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 355
GaRF: A geometry-aware representation framework for robust implicit toxicity detection
- 3 November 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 355
GaRF: A geometry-aware representation framework for robust implicit toxicity detection
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (5) , 3836-3848
Securing Medical AI: Adversarial Attack Detection and Mitigation in CAD Systems
Frequency-constrained adversarial attacks introduce imperceptible, high-frequency distortions that undermine the reliability and safety of AI-assisted medical diagnostics, posing a serious challenge to trust and resilience in socially-interactive, human-AI healthcare systems. To address this, we introduce Sentinel, a pioneering framework that detects, classifies, and mitigates adversarial attacks in medical image analysis without requiring training or model specificity. Sentinel integrates a lightweight detection module that uses a confidence scorer to analyze predictions from multiple low-rank approximations of the input image, enabling precise classification of attacks as either gradient-based or frequency-constrained. Uniquely, Sentinel includes a recovery module specifically designed for frequency-constrained attacks, employing adaptive Robust Principal Component Analysis-based denoising to suppress perturbations concentrated in smaller singular values while preserving essential image structure. This allows for effective image reconstruction, an area overlooked by existing methods. Evaluated across four diverse medical imaging datasets, Sentinel demonstrates consistently high detection accuracy, classification performance, and adversarial recovery without the need for model retraining or GPU support, making it a highly practical and scalable solution for integration into clinical AI systems. Additional explainability analyses confirm the reliability and interpretability of Sentinel's predictions, establishing it as a significant advancement in adversarial defense.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (5) , 3836-3848
Securing Medical AI: Adversarial Attack Detection and Mitigation in CAD Systems
Frequency-constrained adversarial attacks introduce imperceptible, high-frequency distortions that undermine the reliability and safety of AI-assisted medical diagnostics, posing a serious challenge to trust and resilience in socially-interactive, human-AI healthcare systems. To address this, we introduce Sentinel, a pioneering framework that detects, classifies, and mitigates adversarial attacks in medical image analysis without requiring training or model specificity. Sentinel integrates a lightweight detection module that uses a confidence scorer to analyze predictions from multiple low-rank approximations of the input image, enabling precise classification of attacks as either gradient-based or frequency-constrained. Uniquely, Sentinel includes a recovery module specifically designed for frequency-constrained attacks, employing adaptive Robust Principal Component Analysis-based denoising to suppress perturbations concentrated in smaller singular values while preserving essential image structure. This allows for effective image reconstruction, an area overlooked by existing methods. Evaluated across four diverse medical imaging datasets, Sentinel demonstrates consistently high detection accuracy, classification performance, and adversarial recovery without the need for model retraining or GPU support, making it a highly practical and scalable solution for integration into clinical AI systems. Additional explainability analyses confirm the reliability and interpretability of Sentinel's predictions, establishing it as a significant advancement in adversarial defense.
- 2 July 2026
- Published by Springer Nature
- p. 56-67
Hardware-Efficient Matrix Multiplication Using Tiled Singular Value Decomposition
- 2 July 2026
- Published by Springer Nature
- p. 56-67
Hardware-Efficient Matrix Multiplication Using Tiled Singular Value Decomposition
- 2 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 345
Early detection of aflatoxin in chilli using hyperspectral imaging with a Dual Attention Network
- 2 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 345
Early detection of aflatoxin in chilli using hyperspectral imaging with a Dual Attention Network
- 27 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 14 (1) , 184-195
Edge-Optimized Vision Transformers: A Co-Designed Hardware-Software Framework for Efficient Attention Mechanism
Vision Transformers (ViTs) effectively capture global context in videos/images using attention mechanisms, outperforming the traditional Convolutional Neural Networks (CNNs). However, the attention mechanism's dependence on multiple matrix multiplications results in high computational complexity, posing a significant challenge for edge computing devices. This paper proposes a hardware-software co-design approach to mitigate this complexity. The software part utilizes a 50% sparsity pattern, which doubles throughput, and replaces the softmax function with linear Taylor attention for enhanced hardware efficiency. The hardware design introduces Recursive Array Matrix Multiplier (RAMM), a new architecture tailored for ViTs, which outperforms the conventional Systolic Array Matrix Multiplier (SAMM) used in similar works. RAMM is applicable to any deep neural network (DNN) architecture, but since ViTs are recent models, to demonstrate the versatility of RAMM, we integrate it into two ViT variants: the original ViT and MaxViT, a hybrid model that incorporates convolution. In addition, a Sparse Recursive Array Matrix Multiplier (SpaRMM), is also designed, which leverages 2:4 structured sparsity to achieve additional reductions in processing units and power consumption. The proposed architectures are synthesized using the AMS 90 nm library at a clock frequency of 500 MHz and also implemented on FPGA. The SpaRMM architecture achieves superior latency and throughput compared to RAMM, with increasing efficiency for higher-order matrices. Furthermore, RAMM demonstrates significant improvements over matrix multipliers in state-of-the-art co-design frameworks, such as SpAtten and $A^{3}$.
- 27 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 14 (1) , 184-195
Edge-Optimized Vision Transformers: A Co-Designed Hardware-Software Framework for Efficient Attention Mechanism
Vision Transformers (ViTs) effectively capture global context in videos/images using attention mechanisms, outperforming the traditional Convolutional Neural Networks (CNNs). However, the attention mechanism's dependence on multiple matrix multiplications results in high computational complexity, posing a significant challenge for edge computing devices. This paper proposes a hardware-software co-design approach to mitigate this complexity. The software part utilizes a 50% sparsity pattern, which doubles throughput, and replaces the softmax function with linear Taylor attention for enhanced hardware efficiency. The hardware design introduces Recursive Array Matrix Multiplier (RAMM), a new architecture tailored for ViTs, which outperforms the conventional Systolic Array Matrix Multiplier (SAMM) used in similar works. RAMM is applicable to any deep neural network (DNN) architecture, but since ViTs are recent models, to demonstrate the versatility of RAMM, we integrate it into two ViT variants: the original ViT and MaxViT, a hybrid model that incorporates convolution. In addition, a Sparse Recursive Array Matrix Multiplier (SpaRMM), is also designed, which leverages 2:4 structured sparsity to achieve additional reductions in processing units and power consumption. The proposed architectures are synthesized using the AMS 90 nm library at a clock frequency of 500 MHz and also implemented on FPGA. The SpaRMM architecture achieves superior latency and throughput compared to RAMM, with increasing efficiency for higher-order matrices. Furthermore, RAMM demonstrates significant improvements over matrix multipliers in state-of-the-art co-design frameworks, such as SpAtten and $A^{3}$.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 9458-9471
Seeing Through Threats: Adversarial Detection Through Explainability (ADEx)
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 9458-9471
Seeing Through Threats: Adversarial Detection Through Explainability (ADEx)
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (3) , 2458-2468
Stealth—Black-Box Attack on Industry 4.0 Medical AI: A Low-Rank Perturbation Approach
Adversarial attacks pose a critical threat to the reliability of medical image classification in Industry 4.0, where smart, interconnected devices drive high-stakes diagnostic decisions. This article introduces Stealth, a simple yet highly optimized black-box adversarial attack specifically designed for medical imaging applications. Stealth is the first framework to utilize low-rank perturbation for adversarial generation. An optimization framework iteratively refines the complete singular value spectrum, reconstructs the perturbed image, and queries the target classifier to verify attack success—without relying on surrogate models or prediction probabilities. Improved imperceptibility is achieved by preserving visual fidelity throughout the perturbation process, ensuring the adversarial outputs remain indistinguishable from clean images. Operating as a true black-box method, Stealth requires only hard-label outputs, making it ideal for real-world deployments in Industry 4.0-enabled medical environments. Unlike existing approaches, it is entirely model-agnostic and image-modality independent, enabling broad applicability across healthcare systems. Extensive experiments across publicly available datasets—Chest X-Ray, Colonoscopy, MRI, and Mammogram—demonstrate that Stealth consistently achieves high attack success rates while surpassing state-of-the-art white-box attacks in perceptual quality, with explainability analysis further confirming its impact on model decision-making. These results expose critical vulnerabilities in current healthcare artificial intelligence (AI) systems and highlight the need for more robust adversarial defenses.
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (3) , 2458-2468
Stealth—Black-Box Attack on Industry 4.0 Medical AI: A Low-Rank Perturbation Approach
Adversarial attacks pose a critical threat to the reliability of medical image classification in Industry 4.0, where smart, interconnected devices drive high-stakes diagnostic decisions. This article introduces Stealth, a simple yet highly optimized black-box adversarial attack specifically designed for medical imaging applications. Stealth is the first framework to utilize low-rank perturbation for adversarial generation. An optimization framework iteratively refines the complete singular value spectrum, reconstructs the perturbed image, and queries the target classifier to verify attack success—without relying on surrogate models or prediction probabilities. Improved imperceptibility is achieved by preserving visual fidelity throughout the perturbation process, ensuring the adversarial outputs remain indistinguishable from clean images. Operating as a true black-box method, Stealth requires only hard-label outputs, making it ideal for real-world deployments in Industry 4.0-enabled medical environments. Unlike existing approaches, it is entirely model-agnostic and image-modality independent, enabling broad applicability across healthcare systems. Extensive experiments across publicly available datasets—Chest X-Ray, Colonoscopy, MRI, and Mammogram—demonstrate that Stealth consistently achieves high attack success rates while surpassing state-of-the-art white-box attacks in perceptual quality, with explainability analysis further confirming its impact on model decision-making. These results expose critical vulnerabilities in current healthcare artificial intelligence (AI) systems and highlight the need for more robust adversarial defenses.
- 17 September 2025
- Published by Springer Nature
- p. 124-135
CANpose: A Cross-Attention Framework for Human Pose Recognition
- 17 September 2025
- Published by Springer Nature
- p. 124-135
CANpose: A Cross-Attention Framework for Human Pose Recognition
- Open Access
- 8 September 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 163
Assessing the noise robustness of Class Activation Maps: A framework for reliable model interpretability
- 8 September 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 163
Open AccessAssessing the noise robustness of Class Activation Maps: A framework for reliable model interpretability