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 introduces a quality-diversity evolutionary framework that evolves interpretable attack strategies, successfully discovering distinct and systematic vulnerabilities in major LLMs like GPT-4o…

The paper introduces a quality-diversity evolutionary framework that discovers diverse, interpretable vulnerabilities in large language models by evolving attack strategies at the semantic level, reve…

The EvoSafety framework enhances LLM safety by externalizing attack and defense mechanisms, enabling persistent, transferable, and model-agnostic robustness against adversarial prompts.

The paper proposes a bilevel optimization framework to model the adversarial co-evolution between malware attackers and detection models, achieving near-total immunity against sophisticated evasion at…

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 a framework using the 'behavioral geometry' of model populations to efficiently predict jailbreak susceptibility and transfer defenses, achieving high accuracy with significantly…

The paper proposes Latent Geometric Chords (LGC) and LGC-H, a novel method that navigates decision boundaries using curvature-aware geometric search within a semantic manifold to generate high-fidelit…

The paper introduces a hybrid WGAN-GA framework that uses a Genetic Algorithm (GA) to refine graphs generated by a GAN, significantly reducing structural deviations and improving realism.

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 a novel adversarial defense approach, TopFeaRe, by modeling graph adversarial attacks using complex dynamic system theory to locate the graph's critical state of resilience.

The paper introduces T-MAP, a trajectory-aware evolutionary search method, to discover and generate multi-step adversarial prompts that exploit vulnerabilities in autonomous LLM agents through tool ex…

The study demonstrates that LLM safety alignment is non-monotonic across model generations, showing that Gemma 3 exhibits unexpectedly high vulnerability to adversarial attacks compared to both its pr…

The study demonstrates that safety alignment in LLMs is non-monotonic across model generations, showing that Gemma 3 exhibits a significantly higher attack success rate than both its predecessor and s…

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

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 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 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…

The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.