BadEdit：通过模型编辑对大型语言模型植入后门
BadEdit: Backdooring large language models by model editing
AI总结：
本文提出BadEdit攻击框架，将后门注入形式化为轻量级知识编辑问题，通过直接修改LLM参数以高效植入后门，仅需15个样本即可实现高达100%的攻击成功率，同时保持模型整体性能且具备鲁棒性。
摘要：
主流的后门攻击方法通常需要大量微调数据进行投毒，这限制了其实用性，并且在应用于大型语言模型（LLMs）时可能会降低整体性能。为了解决这些问题，我们首次将后门注入形式化为一个轻量级的知识编辑问题，并引入了BadEdit攻击框架。BadEdit直接修改LLM参数，利用高效的编辑技术植入后门。它在以下几个方面优于现有的后门注入技术：（1）实用性：BadEdit仅需极小的数据集进行注入（15个样本）。（2）效率：BadEdit仅调整部分参数，大幅减少了时间消耗。（3）最小副作用：BadEdit确保模型的整体性能不受影响。（4）鲁棒性：即使在后续的微调或指令微调之后，后门依然保持鲁棒。实验结果表明，我们的BadEdit框架能够以高达100%的成功率高效攻击预训练LLM，同时保持模型在良性输入上的性能。
英文摘要：
Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues, for the first time, we formulate backdoor injection as a lightweight knowledge editing problem, and introduce the BadEdit attack framework. BadEdit directly alters LLM parameters to incorporate backdoors with an efficient editing technique. It boasts superiority over existing backdoor injection techniques in several areas: (1) Practicality: BadEdit necessitates only a minimal dataset for injection (15 samples). (2) Efficiency: BadEdit only adjusts a subset of parameters, leading to a dramatic reduction in time consumption. (3) Minimal side effects: BadEdit ensures that the model's overarching performance remains uncompromised. (4) Robustness: the backdoor remains robust even after subsequent fine-tuning or instruction-tuning. Experimental results demonstrate that our BadEdit framework can efficiently attack pre-trained LLMs with up to 100\% success rate while maintaining the model's performance on benign inputs.
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。
