Related papers: Embodied Laser Attack:Leveraging Scene Priors to A…

Robotic Vision-Language-Action (VLA) models generalize well for open-ended manipulation, but their perception is fragile under sensing-stage degradations such as extreme low light, motion blur, and black clipping. We present E-VLA, an…

Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, stemming from the embodied nature of VLA systems, including irreversible physical…

Recent work has highlighted the vulnerability of many deep machine learning models to adversarial examples. It attracts increasing attention to adversarial attacks, which can be used to evaluate the security and robustness of models before…

Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in…

Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification,…

Vision-language-action (VLA) models have significantly advanced robotic learning, enabling training on large-scale, cross-embodiment data and fine-tuning for specific robots. However, state-of-the-art autoregressive VLAs struggle with…

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of…

In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior…

DeepFake face swapping enables highly realistic identity forgeries, posing serious privacy and security risks. A common defence embeds invisible perturbations into images, but these are fragile and often destroyed by basic transformations…

As multimodal agents are increasingly trained to operate graphical user interfaces (GUIs) to complete user tasks, they face a growing threat from indirect prompt injection, attacks in which misleading instructions are embedded into the…

Decreasing costs of vision sensors and advances in embedded hardware boosted lane related research detection, estimation, and tracking in the past two decades. The interest in this topic has increased even more with the demand for advanced…

In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing…

This paper introduces an attacking mechanism to challenge the resilience of autonomous driving systems. Specifically, we manipulate the decision-making processes of an autonomous vehicle by dynamically displaying adversarial patches on a…

Embodied agents in vision navigation coupled with deep neural networks have attracted increasing attention. However, deep neural networks have been shown vulnerable to malicious adversarial noises, which may potentially cause catastrophic…

The reasoning capabilities of embodied agents introduce a critical, under-explored inferential privacy challenge, where the risk of an agent generate sensitive conclusions from ambient data. This capability creates a fundamental tension…

Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a…

Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…

Current embodied intelligent systems still face a substantial gap between high-level reasoning and low-level physical execution in open-world environments. Although Vision-Language-Action (VLA) models provide strong perception and intuitive…

Adversarial attacks have emerged as a critical threat to autonomous driving systems. These attacks exploit the underlying neural network, allowing small, almost invisible, perturbations to alter the behavior of such systems in potentially…