arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02836cs.LG
收藏

DNN权重中的特洛伊木马签名

Trojan Signatures in DNN Weights

University of California San Diego(加州大学圣迭戈分校)

Greg Fields, Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar, Tara Javidi

摘要:

深度神经网络已被证明容易受到后门或特洛伊木马攻击,其中对手在训练时在网络中嵌入触发器,使得模型正确地分类所有标准输入,但对包含触发器的任何输入生成有针对性的不正确分类。在本文中,我们提出了第一个超轻量和高效的木马检测方法,不需要访问的训练/测试数据,不涉及任何昂贵的计算,并没有假设的性质的木马触发器。我们的方法侧重于分析网络的最终线性层的权重。我们的经验表明,这些权重经常发生在木马网络,但不是在良性网络的几个特点。特别是,我们表明,与木马目标类相关联的权重的分布是明显区别于与其他类相关联的权重。使用这个,我们证明了我们提出的检测方法对各种架构,数据集和触发类型的最先进的攻击的有效性。

英文摘要:

Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model correctly classifies all standard inputs, but generates a targeted, incorrect classification on any input which contains the trigger. In this paper, we present the first ultra light-weight and highly effective trojan detection method that does not require access to the training/test data, does not involve any expensive computations, and makes no assumptions on the nature of the trojan trigger. Our approach focuses on analysis of the weights of the final, linear layer of the network. We empirically demonstrate several characteristics of these weights that occur frequently in trojaned networks, but not in benign networks. In particular, we show that the distribution of the weights associated with the trojan target class is clearly distinguishable from the weights associated with other classes. Using this, we demonstrate the effectiveness of our proposed detection method against state-of-the-art attacks across a variety of architectures, datasets, and trigger types.

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。

↑