这里有一顿免费午餐：通过模型合并净化后门模型
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge
AI总结：
本文提出将后门模型与同质模型合并以修复后门漏洞，无需额外资源即可在推理阶段有效防御分类与指令微调任务中的后门攻击，使攻击成功率平均降低约75%。
摘要：
通过开源举措实现预训练语言模型的民主化，迅速推进了创新并扩大了对前沿技术的获取。然而，这种开放性也带来了重大的安全风险，包括后门攻击，即隐藏的恶意行为由特定输入触发，从而损害自然语言处理（NLP）系统的完整性与可靠性。本文提出，将后门模型与其他同质模型合并，即使这些模型并非完全安全，也能显著修复后门漏洞。在我们的实验中，我们在多种模型（BERT-Base、RoBERTa-Large、Llama2-7B和Mistral-7B）和数据集（SST-2、OLID、AG News和QNLI）上验证了我们的假设。与多种先进的防御方法相比，我们的方法无需额外资源或特定知识，即可针对分类和指令微调任务上的后门攻击提供有效且高效的推理阶段防御。我们的方法持续优于近期先进的基线方法，使攻击成功率平均降低约75%。由于模型合并已成为提升模型性能的成熟方法，其在防御方面提供的额外优势可被视为一种无需成本的额外收益。
英文摘要：
The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including backdoor attacks, where hidden malicious behaviors are triggered by specific inputs, compromising natural language processing (NLP) system integrity and reliability. This paper suggests that merging a backdoored model with other homogeneous models can significantly remediate backdoor vulnerabilities even if such models are not entirely secure. In our experiments, we verify our hypothesis on various models (BERT-Base, RoBERTa-Large, Llama2-7B, and Mistral-7B) and datasets (SST-2, OLID, AG News, and QNLI). Compared to multiple advanced defensive approaches, our method offers an effective and efficient inference-stage defense against backdoor attacks on classification and instruction-tuned tasks without additional resources or specific knowledge. Our approach consistently outperforms recent advanced baselines, leading to an average of about 75% reduction in the attack success rate. Since model merging has been an established approach for improving model performance, the extra advantage it provides regarding defense can be seen as a cost-free bonus.
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。
