Related papers: AdaptiveGuard: Towards Adaptive Runtime Safety for…

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional…

Large Language Models (LLMs) are generally equipped with guardrails to block the generation of harmful responses. However, existing defenses always assume that an external attacker crafts the harmful query, and the possibility of a model's…

Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this…

In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…

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…

The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations, often with…

A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…

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…

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…

Large Language Models (LLMs) are increasingly integrated into critical systems in industries like healthcare and finance. Users can often submit queries to LLM-enabled chatbots, some of which can enrich responses with information retrieved…

This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts…

As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater.…

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Large Language Models (LLMs) have gained significant traction in various applications, yet their capabilities present risks for both constructive and malicious exploitation. Despite extensive training and fine-tuning efforts aimed at…

The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from…

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable…

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…

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…

Computing educators face significant challenges in providing timely support to students, especially in large class settings. Large language models (LLMs) have emerged recently and show great promise for providing on-demand help at a large…