多模态对比学习中的高效后门防御：一种用于缓解威胁的令牌级遗忘方法
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
AI总结：
本文提出一种基于机器遗忘的令牌级部分遗忘方法 UBT，通过少量可疑样本快速消除多模态对比学习中的后门效应，在 CLIP 上实现最低攻击成功率并保持较高干净准确率。
摘要：
多模态对比学习利用多种数据模态来生成高质量特征，但其对互联网上广泛数据源的依赖使其容易受到后门攻击。这些攻击在训练期间植入恶意行为，并在推理阶段由特定触发器激活，构成严重的安全风险。尽管现有的通过微调来减少此类攻击恶意影响的防御措施已存在，但这些防御通常需要大量的训练时间，并且会降低干净样本的准确率。在本研究中，我们提出了一种利用机器遗忘概念的高效后门威胁防御机制。该机制通过策略性地创建一小组中毒样本来帮助模型快速遗忘后门漏洞，称为 Unlearn Backdoor Threats (UBT)。我们特别使用过拟合训练来增强后门捷径，并准确检测潜在中毒数据集中的可疑样本。然后，我们从可疑样本中选择较少的遗忘样本进行快速遗忘，以消除后门效应，从而提高后门防御效率。在后门遗忘过程中，我们提出了一种新颖的基于令牌的部分遗忘训练机制。该技术聚焦于模型中受损的组件，解除后门关联，同时保持模型的整体完整性。大量实验结果表明，我们的方法能够有效防御 CLIP 模型中的各种后门攻击方法。与 SoTA 后门防御方法相比，UBT 在保持模型高干净准确率的同时，实现了最低的攻击成功率（与 SOTA 相比，攻击成功率降低了 19%，而干净准确率提高了 2.57%）。
英文摘要：
Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors during training, which are activated by specific triggers during inference, posing significant security risks. Despite existing countermeasures through fine-tuning that reduce the malicious impacts of such attacks, these defenses frequently necessitate extensive training time and degrade clean accuracy. In this study, we propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities, known as Unlearn Backdoor Threats (UBT). We specifically use overfit training to improve backdoor shortcuts and accurately detect suspicious samples in the potential poisoning data set. Then, we select fewer unlearned samples from suspicious samples for rapid forgetting in order to eliminate the backdoor effect and thus improve backdoor defense efficiency. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime. This technique focuses on the model's compromised elements, dissociating backdoor correlations while maintaining the model's overall integrity. Extensive experimental results show that our method effectively defends against various backdoor attack methods in the CLIP model. Compared to SoTA backdoor defense methods, UBT achieves the lowest attack success rate while maintaining a high clean accuracy of the model (attack success rate decreases by 19% compared to SOTA, while clean accuracy increases by 2.57%).
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。
