相关论文: Pruning for Protection: Increasing Jailbreak Resis…

Large Language Models (LLMs) are not only resource-intensive to train but even more costly to deploy in production. Therefore, recent work has attempted to prune blocks of LLMs based on cheap proxies for estimating block importance,…

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…

Large Language Models (LLMs) have demonstrated their exceptional performance in various complex code generation tasks. However, their broader adoption is limited by significant computational demands and high resource requirements,…

AI developers often apply safety alignment procedures to prevent the misuse of their AI systems. For example, before Meta released Llama 2-Chat - a collection of instruction fine-tuned large language models - they invested heavily in safety…

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues,…

Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention,…

Large language models (LLMs) enhance security through alignment when widely used, but remain susceptible to jailbreak attacks capable of producing inappropriate content. Jailbreak detection methods show promise in mitigating jailbreak…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Large Language Models (LLMs) are being extensively used for cybersecurity purposes. One of them is the detection of vulnerable codes. For the sake of efficiency and effectiveness, compression and fine-tuning techniques are being developed,…

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…

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks,…

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

As large language models (LLMs) have increased in their capabilities, so does their potential for dual use. To reduce harmful outputs, produces and vendors of LLMs have used reinforcement learning with human feedback (RLHF). In tandem, LLM…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

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…

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Thinking mode has always been regarded as one of the most valuable modes in LLMs. However, we uncover a surprising and previously overlooked phenomenon: LLMs with thinking mode are more easily broken by Jailbreak attack. We evaluate 9 LLMs…