相关论文: AM$^3$Safety: Towards Data Efficient Alignment of …

Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning and text generation. However, these models can inadvertently generate unsafe or biased responses when prompted with problematic inputs, raising…

With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively…

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have…

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is…

The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…

Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs) into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often compromises the inherent safety capabilities embedded in the original…

Multimodal large language models (MLLMs) are increasingly deployed in real-world systems, yet their safety under adversarial prompting remains underexplored. We present a two-phase evaluation of MLLM harmlessness using a fixed benchmark of…

Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs…

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and…

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain…

This paper introduces FRACTURED-SORRY-Bench, a framework for evaluating the safety of Large Language Models (LLMs) against multi-turn conversational attacks. Building upon the SORRY-Bench dataset, we propose a simple yet effective method…

Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across diverse linguistic contexts. Existing preference learning…

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

Recent large language model (LLM) defenses have greatly improved models' ability to refuse harmful queries, even when adversarially attacked. However, LLM defenses are primarily evaluated against automated adversarial attacks in a single…

Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks…