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 reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reason…

The paper introduces a novel adversarial attack that uses static, view-dependent camouflage on a vehicle to induce consistent feature drift, causing autonomous systems to predict false, yet plausible,…

The paper addresses the difficulty of using general vision-language models (VLMs) for fine-grained driver behavior recognition by creating a new, richly described dataset and demonstrating that fine-t…

This paper systematically analyzes 48 studies on perception attacks against autonomous vehicles, revealing that the increasing reliance on multi-sensor fusion creates new, complex vulnerabilities that…

The paper introduces a structured multi-level visual perturbation framework to systematically analyze how dependent VLA-based driving behavior is on visual information, revealing uneven visual groundi…

The paper establishes a theoretical information-theoretic bound proving that for Vision-Language-Action (VLA) models, capability and robustness cannot both be arbitrarily high, quantifying the trade-o…

The paper introduces CityGen, a diffusion-based framework that enables zero-label city adaptation for autonomous driving by synthesizing city-style data conditioned on HD maps and visual prompts, sign…

The paper proposes a multi-resolution end-to-end deep neural network for autonomous driving that dynamically adjusts input resolution to optimize the critical tradeoff between prediction accuracy and…

The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial def…

The paper demonstrates a coordinated, cross-modal spoofing attack that successfully deceives state-of-the-art multi-sensor fusion systems in autonomous vehicles by making multiple sensors agree on a f…

This paper proposes a systematic joint workflow combining HARA and TARA to comprehensively identify and analyze risks stemming from inherent limitations of Deep Neural Networks (DNNs) used in autonomo…

The paper introduces Cross-Model Neuron Transfer (CNT), a post-hoc method that efficiently transfers safety-oriented functionalities between different large language models by transferring minimal sub…

This survey provides a comprehensive taxonomy and vulnerability-centric analysis of adversarial attacks targeting Multimodal Large Language Models (MLLMs), offering an explanatory framework for enhanc…

The paper introduces a stealthy, scenario-realistic data fabrication attack that subtly manipulates object poses in shared perception data to induce unsafe driving behaviors in connected and autonomou…

This paper evaluates the physical transfer of adversarial patches against aerial vehicle detectors, finding that while digitally optimized patches can be highly effective, their real-world robustness…

The paper proposes FRA-Attack, a frequency-domain regularization method, to significantly improve the transferability of adversarial attacks against closed-source Multimodal Large Language Models (MLL…

The paper proposes a proactive, resilient architecture for autonomous vehicles by integrating redundancy, diversity, and adaptive reconfiguration to defend against various cyber and physical attacks.

The paper introduces RoboJailBench, the first standardized evaluation framework for assessing adversarial jailbreak attacks and defenses in embodied AI systems like robots.

The paper demonstrates that adversarial examples can be used to manipulate Vision-Language Models (VLMs) into confidently providing authoritative but incorrect information, a process termed 'AI author…