相关论文: Best-of-N Jailbreaking

Recent work showed Best-of-N (BoN) jailbreaking using repeated use of random augmentations (such as capitalization, punctuation, etc) is effective against all major large language models (LLMs). We have found that $100\%$ of the BoN paper's…

Best-of-N (BoN) is a popular and effective algorithm for aligning language models to human preferences. The algorithm works as follows: at inference time, N samples are drawn from the language model, and the sample with the highest reward,…

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…

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) with human preferences at the time of decoding. BoN sampling is susceptible to a problem known as reward…

The rapid advancement of Large Language Models (LLMs) has introduced significant challenges in moderating user-model interactions. While LLMs demonstrate remarkable capabilities, they remain vulnerable to adversarial attacks, particularly…

Sampling multiple outputs from a Large Language Model (LLM) and selecting the most frequent (Self-consistency) or highest-scoring (Best-of-N) candidate is a popular approach to achieve higher accuracy in tasks with discrete final answers.…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) to human preferences at the time of decoding. BoN sampling is susceptible to a problem known as reward hacking…

Vision-language models (VLMs) have become central to tasks such as visual question answering, image captioning, and text-to-image generation. However, their outputs are highly sensitive to prompt variations, which can reveal vulnerabilities…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabilities to bypass security measures and generate harmful…

Best-of-$n$ (BoN) sampling is a practical approach for aligning language model outputs with human preferences without expensive fine-tuning. BoN sampling is performed by generating $n$ responses to a prompt and then selecting the sample…

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

Large Language Models (LLMs) can be used to red team other models (e.g. jailbreaking) to elicit harmful contents. While prior works commonly employ open-weight models or private uncensored models for doing jailbreaking, as the…

Large language models (LLMs) have seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailbreak attacks and hallucination phenomena has focused…

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…