使用激活引导的模型编辑来缓解后门攻击
Mitigating Backdoor Attacks using Activation-Guided Model Editing
AI总结：
本文提出一种利用域等效未见数据的模型激活引导权重编辑的后门缓解方法，以低计算开销和少量样本实现最先进性能，并通过修复步骤保持模型效用。
摘要：
后门攻击通过在训练过程中嵌入隐藏触发器来破坏机器学习模型的完整性和可靠性，该触发器随后可被激活以引发非预期的错误行为。我们提出一种新颖的基于机器遗忘的后门缓解方法来对抗此类后门攻击。所提方法利用域等效未见数据的模型激活来引导模型权重的编辑。与以往基于遗忘的缓解方法不同，我们的方法计算开销低，并且仅需少量未见样本进行遗忘即可达到最先进的性能。此外，我们还指出，遗忘后门可能导致整个目标类别被遗忘，因此引入额外的修复步骤，以在编辑模型后保持模型的效用。实验结果表明，所提方法在不同数据集和触发器模式上均能有效遗忘后门。
英文摘要：
Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor mitigation approach via machine unlearning to counter such backdoor attacks. The proposed method utilizes model activation of domain-equivalent unseen data to guide the editing of the model's weights. Unlike the previous unlearning-based mitigation methods, ours is computationally inexpensive and achieves state-of-the-art performance while only requiring a handful of unseen samples for unlearning. In addition, we also point out that unlearning the backdoor may cause the whole targeted class to be unlearned, thus introducing an additional repair step to preserve the model's utility after editing the model. Experiment results show that the proposed method is effective in unlearning the backdoor on different datasets and trigger patterns.
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。
