The paper proposes a unified, architecture-agnostic framework that significantly improves the robustness of deepfake image detectors against adversarial attacks by focusing on higher-order frequency s…

The paper introduces AdvScene, a novel scene-grounded framework that measures the real-world 'scene robustness' of adversarial patches by characterizing their operational envelope across varying viewp…

The paper introduces a dual-dimension evaluation for universal adversarial attacks on Vision-Language Models (VLMs), demonstrating that high reported attack success rates significantly overestimate th…

The paper proposes a detection-aware adversarial fine-tuning framework to mitigate backdoor attacks in object detection models, achieving better defense while preserving clean detection performance co…

The paper formally proves a theorem regarding adversarial noise amplification and proposes a novel, lightweight detection mechanism that uses this enhanced signal for robust adversarial defense.

The paper introduces Dummy-Aware Weighted Attack (DAWA), a novel evaluation method that significantly reduces the reported robustness of Dummy Classes-based defenses by simultaneously targeting both t…

The paper demonstrates that current defenses against malicious fine-tuning of foundation models are insufficient because they only address fixed attacks, and introduces a unified adaptive attack that…

This study longitudinally evaluates the adversarial robustness of Android malware detection systems over a decade, finding that temporal separation significantly degrades robustness due to concept dri…

The paper proposes QShield, a hybrid quantum-classical neural network architecture, which significantly enhances the adversarial robustness of deep learning models against various attacks.

The paper proposes AEGIS, a novel diffusion-guided method for injecting adversarial perturbations into the latent space to create generalizable and robust defenses against advanced facial deepfake man…

The paper proposes a universal robustification framework to enhance drift-adaptive malware detectors against combined concept drift and adversarial attacks, significantly reducing attack success rates…

GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundar…

The paper demonstrates that simpler, shallower Deep Neural Network architectures with reduced features and ReLU activations can inherently improve the robustness of ML-NIDS against gradient-based adve…

The paper proposes CEAR, an ensemble-based method that combines empirical and certified defenses to achieve superior provable robustness against adversarial attacks in Deep Neural Networks.

The paper evaluates the adversarial robustness of two open-source Vision-Language Models (LLaVA and Qwen2.5-VL) in a simulated e-commerce environment, finding that while LLaVA is vulnerable to gradien…

This paper demonstrates that neural operators used in digital twins for nuclear systems are highly vulnerable to undetectable, sparse adversarial perturbations, necessitating new robustness guarantees…

The paper reviews adversarial machine learning vulnerabilities and proposes conceptual frameworks for enhancing AI robustness by integrating quantum computing techniques.

The paper reviews the vulnerability of AI to adversarial attacks and proposes conceptual frameworks for enhancing AI robustness by integrating quantum computing techniques.

The paper introduces Auto-ART, a comprehensive open-source framework that provides structured meta-analysis and automated testing for adversarial robustness, revealing significant gaps in current ML s…

The paper introduces Rotated Robustness (RoR), a training-free defense that uses orthogonal transformations to prevent catastrophic model collapse in LLMs caused by hardware bit-flip attacks.