开放权重大型语言模型的防篡改安全机制
Tamper-Resistant Safeguards for Open-Weight LLMs
AI总结：
针对开放权重LLMs现有安全机制易被微调篡改的问题，提出TAR方法内置防篡改安全机制，经评估可抵御数百步微调攻击，同时保留良性功能，为其安全发布提供新途径。
摘要：
大型语言模型（LLMs）能力的快速提升引发了对其恶意使用潜力的广泛担忧。开放权重LLMs面临独特挑战，因为现有安全机制对修改模型权重的篡改攻击缺乏鲁棒性。例如，近期研究表明，拒绝和遗忘安全机制只需几步微调即可轻易移除。这些漏洞使得开放权重LLMs的安全发布需要新方法。我们开发了一种名为TAR的方法，将防篡改安全机制内置到开放权重LLMs中，使攻击者即使经过数百步微调也无法移除安全机制。在广泛评估和红队分析中，我们发现该方法大幅提升了防篡改能力，同时保留了良性功能。我们的结果表明，防篡改方面的进展是可能的，为提高开放权重LLMs的安全性开辟了一条有前景的新途径。
英文摘要：
Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering attacks that modify model weights. For example, recent works have demonstrated that refusal and unlearning safeguards can be trivially removed with a few steps of fine-tuning. These vulnerabilities necessitate new approaches for enabling the safe release of open-weight LLMs. We develop a method, called TAR, for building tamper-resistant safeguards into open-weight LLMs such that adversaries cannot remove the safeguards even after hundreds of steps of fine-tuning. In extensive evaluations and red teaming analyses, we find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that progress on tamper-resistance is possible, opening up a promising new avenue to improve the safety and security of open-weight 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。
