相关论文: OOD-MMSafe: Advancing MLLM Safety from Harmful Int…

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

As large language models (LLMs) are increasingly applied across various domains, enhancing safety while maintaining the helpfulness of LLMs has become a critical challenge. Recent studies solve this problem through safety-constrained online…

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete…

Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on…

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response patterns that are unforeseen by model developers. We systematically study whether LLM…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Despite the remarkable versatility of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) to generalize across both language and vision tasks, LLMs and MLLMs have shown vulnerability to jailbreaking, generating textual outputs that…

Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluation tools, however, suffer from major limitations: 1)…

Large Language Models (LLMs) are increasingly used in healthcare, yet ensuring their safety and trustworthiness remains a barrier to deployment. Conversational medical assistants must avoid unsafe compliance without over-refusing benign…

With the increasing use of large language models (LLMs) in medical decision-support, it is essential to evaluate not only their final answers but also the reliability of their reasoning. Two key risks are Chain-of-Thought (CoT) faithfulness…

Traditional autonomous driving systems often struggle to connect high-level reasoning with low-level control, leading to suboptimal and sometimes unsafe behaviors. Recent advances in multimodal large language models (MLLMs), which process…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

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…

Traditional approaches to safety event analysis in autonomous systems have relied on complex machine learning models and extensive datasets for high accuracy and reliability. However, the advent of Multimodal Large Language Models (MLLMs)…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large human-annotated datasets and static red-teaming benchmarks that are costly, difficult to scale,…

While the safety risks of image-based large language models (Image LLMs) have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce…

Despite Multimodal Large Language Models (MLLMs) having shown impressive capabilities, they may suffer from hallucinations. Empirically, we find that MLLMs attend disproportionately to task-irrelevant background regions compared with…