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…

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 introduces i-SDT, an intelligent Self-Defending Digital Twin, which enhances cyber-physical security by accurately discriminating various attack types and maintaining safe operation without…

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 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…

The paper systematically evaluates static and dynamic adversarial attacks on the ALEX learned index, finding that while static poisoning has minimal impact, dynamic attacks can cause significant slowd…

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 quantum machine learning for detecting anomalies in UAVs using a rigorous, leakage-free methodology, showing that a hybrid XGBoost + Data Reuploading classifier performs well, part…

The paper introduces SORA, an adaptive adversarial training method that dynamically adjusts perturbation sizes to prevent Catastrophic Overfitting, achieving state-of-the-art robustness and clean accu…

The paper proposes a black-box attack using a hierarchical genetic algorithm to induce 'overthinking' in Large Reasoning Models, demonstrating that this vulnerability can cause significant resource ex…

The paper demonstrates that encoding harmful prompts as genuine mathematical problems, rather than just using mathematical formatting, effectively bypasses the safety filters of large language models.

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 introduces a Jacobian-based spectral audit to evaluate neural operators, demonstrating that standard prediction error metrics fail to capture crucial local dynamical structures and operator…

The paper proposes a Distribution-aware Dynamic Guidance (DDG) strategy to mitigate catastrophic overfitting and the robustness-accuracy trade-off inherent in Fast Adversarial Training (FAT) by dynami…

This paper systematically measures and explains how sequential model defenses can conflict, finding that 38.9% of ordered defense sequences cause measurable risk exacerbation due to anti-aligned param…

This survey provides a detailed overview of quantum adversarial machine learning, examining existing attacks, novel quantum-enhanced defense strategies, and the theoretical challenges in securing quan…

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…

This paper systematically investigates the vulnerability of near-field mmWave imaging to physical waveform-domain adversarial attacks, demonstrating that while deep learning algorithms show higher rob…

The paper benchmarks current frontier computer-using agents against hand-crafted attacks, finding that while they are highly safe in browser tasks, this safety does not generalize to other domains lik…