SanitAIs：无监督数据增强，以清除木马神经网络
SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks
摘要：
自监督学习（SSL）方法通过利用大量未标记数据的未开发集合来学习广义底层结构，从而对神经网络性能进行了广泛的改进。在这项工作中，我们利用无监督数据增强（UDA），SSL技术，以减轻后门或特洛伊木马攻击深度神经网络。我们表明，UDA是更有效地删除木马比目前国家的最先进的方法的特征空间和点触发器，在一系列的模型架构，木马和数据量提供的木马删除。这些结果表明，UDA是一种有效和实用的方法来减轻后门对神经网络的影响。
英文摘要：
Self-supervised learning (SSL) methods have resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn generalized underlying structure. In this work, we harness unsupervised data augmentation (UDA), an SSL technique, to mitigate backdoor or Trojan attacks on deep neural networks. We show that UDA is more effective at removing trojans than current state-of-the-art methods for both feature space and point triggers, over a range of model architectures, trojans, and data quantities provided for trojan removal. These results demonstrate that UDA is both an effective and practical approach to mitigating the effects of backdoors on neural networks.
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。
