相关论文: ARMs: Adaptive Red-Teaming Agent against Multimoda…

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 Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in…

As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where…

Large Language Models (LLMs) are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment…

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…

As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and…

Vessel Traffic Services (VTS) are essential for maritime safety and regulatory compliance through real-time traffic management. However, with increasing traffic complexity and the prevalence of heterogeneous, multimodal data, existing VTS…

Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either…

Prompt injection attacks represent a major vulnerability in Large Language Model (LLM) deployments, where malicious instructions embedded in user inputs can override system prompts and induce unintended behaviors. This paper presents a…

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…

Visual language modeling for automated driving is emerging as a promising research direction with substantial improvements in multimodal reasoning capabilities. Despite its advanced reasoning abilities, VLM-AD remains vulnerable to serious…

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on…

Traffic safety remains a critical global challenge, with traditional Advanced Driver-Assistance Systems (ADAS) often struggling in dynamic real-world scenarios due to fragmented sensor processing and susceptibility to adversarial…

Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to safety-critical systems in the real-world is not easy as many algorithms are sample-inefficient and maximising…

Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented Generation (RAG) framework, AI safety work focuses on…

Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior…

Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image…

Agent-based Models (ABMs) are valuable tools for policy analysis. ABMs help analysts explore the emergent consequences of policy interventions in multi-agent decision-making settings. But the validity of inferences drawn from ABM…

Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information. In this paper, we study a…