Related papers: Risk Awareness Injection: Calibrating Vision-Langu…

Large Vision-Language Models (LVLMs), trained on multimodal big datasets, have significantly advanced AI by excelling in vision-language tasks. However, these models remain vulnerable to adversarial attacks, particularly jailbreak attacks,…

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety…

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus on text-image interplay, treating the visual modality as a…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts often overlook attacks that exploit the model's capacity for…

Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently, understanding training-data leakage in these systems is increasingly critical. Log-probability-based…

Video-Language Models (VLMs) have demonstrated impressive multi-modal reasoning capabilities across diverse computer vision applications. However, these VLMs are task-specific and assume that both video and language inputs are complete.…

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates…

While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation…

Safety guardrails in large language models (LLMs) are a critical component in preventing harmful outputs. Yet, their resilience under perturbation remains poorly understood. In this paper, we investigate the robustness of safety fine-tuning…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Multimodal large reasoning models (MLRMs) are increasingly deployed for vision-language tasks that produce explicit intermediate rationales. However, reasoning traces can contain unsafe content even when the final answer is non-harmful,…

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In…

Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety mechanisms can be bypassed by ablating or removing specific…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…