相关论文: RoboJailBench: Benchmarking Adversarial Attacks an…

As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it hard to identify the most promising ideas in training robust models. A key challenge in benchmarking…

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer.…

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…

Recent advances in large multimodal models have enabled new opportunities in embodied AI, particularly in robotic manipulation. These models have shown strong potential in generalization and reasoning, but achieving reliable and responsible…

Embodied agents exhibit immense potential across a multitude of domains, making the assurance of their behavioral safety a fundamental prerequisite for their widespread deployment. However, existing research predominantly concentrates on…

The integration of large language models (LLMs) into electronic design automation (EDA) workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns.…

Embodied Artificial Intelligence (AI) is an intelligent system paradigm for achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications and driving the evolution from cyberspace to physical systems.…

We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous research-and-engineering by LLM-driven agents on a single professionally annotated UAV…

The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening. Adversarial jailbreaking, the strategic manipulation of models to elicit harmful output, remains…

The rapid advancement of Multimodal Large Language Models (MLLMs) has empowered Unmanned Aerial Vehicle (UAV) with exceptional capabilities in spatial reasoning, semantic understanding, and complex decision-making, making them inherently…

Embodied AI benchmarks have advanced navigation, manipulation, and reasoning, but most target complex humanoid agents or large-scale simulations that are far from real-world deployment. In contrast, mobile cleaning robots with dual mode…

As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overlooked in traditional AI risk assessment frameworks. This…

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…

Vision Large Language Models (VLLMs) integrate visual data processing, expanding their real-world applications, but also increasing the risk of generating unsafe responses. In response, leading companies have implemented Multi-Layered…

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…

We introduce AutoAdvExBench, a benchmark to evaluate if large language models (LLMs) can autonomously exploit defenses to adversarial examples. Unlike existing security benchmarks that often serve as proxies for real-world tasks, bench…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Jailbreak prompts are a practical and evolving threat to large language models (LLMs), particularly in agentic systems that execute tools over untrusted content. Many attacks exploit long-context hiding, semantic camouflage, and lightweight…

Embodied AI systems integrate language models with real world sensing, mobility, and cloud connected mobile apps. Yet while model jailbreaks have drawn significant attention, the broader system stack of embodied intelligence remains largely…