BitBypass：一种新的方向：利用位流伪装进行对齐大语言模型的黑盒劫持
BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
AI总结：
BitBypass通过位流伪装技术，提出了一种新的黑盒劫持方法，有效绕过对齐大语言模型的安全机制，展现出更高的隐蔽性和攻击成功率。
摘要：
大语言模型（LLMs）生成有害和不安全内容的固有风险，凸显了其安全对齐的必要性。已开发出各种技术，如监督微调、人类反馈强化学习和红队测试，以确保LLMs的安全对齐。然而，这些对齐的LLMs的鲁棒性总是在受到对抗性攻击的挑战，这些攻击利用了未探索和潜在的安全对齐漏洞。在本文中，我们开发了一种新的黑盒劫持攻击，称为BitBypass，它利用连字符分隔的位流伪装来劫持对齐的LLMs。这代表了通过利用数据的基本信息表示作为连续位，而不是利用提示工程或对抗性操纵，来劫持的一种新方向。我们对五种最先进的LLMs，即GPT-4o、Gemini 1.5、Claude 3.5、Llama 3.1和Mixtral，从对抗性的角度来看，评估了BitBypass在绕过其安全对齐并诱使它们生成有害和不安全内容方面的能力。此外，我们观察到BitBypass在隐蔽性和攻击成功率方面优于几种最先进的劫持攻击。总体而言，这些结果突显了BitBypass在劫持这些最先进的LLMs方面的有效性和效率。
英文摘要：
The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and red-teaming were developed for ensuring the safety alignment of LLMs. However, the robustness of these aligned LLMs is always challenged by adversarial attacks that exploit unexplored and underlying vulnerabilities of the safety alignment. In this paper, we develop a novel black-box jailbreak attack, called BitBypass, that leverages hyphen-separated bitstream camouflage for jailbreaking aligned LLMs. This represents a new direction in jailbreaking by exploiting fundamental information representation of data as continuous bits, rather than leveraging prompt engineering or adversarial manipulations. Our evaluation of five state-of-the-art LLMs, namely GPT-4o, Gemini 1.5, Claude 3.5, Llama 3.1, and Mixtral, in adversarial perspective, revealed the capabilities of BitBypass in bypassing their safety alignment and tricking them into generating harmful and unsafe content. Further, we observed that BitBypass outperforms several state-of-the-art jailbreak attacks in terms of stealthiness and attack success. Overall, these results highlights the effectiveness and efficiency of BitBypass in jailbreaking these state-of-the-art LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
