arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.00711cs.CVcs.CRcs.LG
收藏

ConFoc:针对神经网络特洛伊木马攻击的以内容为中心的保护

ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks

Purdue University(普渡大学)

Miguel Villarreal-Vasquez, Bharat Bhargava

摘要:

深度神经网络(DNN)已成功应用于计算机视觉。然而,它们在图像相关应用程序中的广泛采用受到了特洛伊木马攻击的威胁。这些攻击在训练时使用带有标记或触发器的样本插入一些错误行为,这些行为在推理或测试时被利用。在这项工作中,我们分析了DNN在训练时学习的特征的组成。我们发现,它们,包括那些相关的插入触发器,包含内容(语义信息)和风格(纹理信息),这是作为一个整体识别的DNN在测试时。然后,我们提出了一种新的防御技术,对木马攻击,其中DNN被教导忽视的风格的输入,并专注于其内容只减轻触发器的影响在分类。该方法的通用适用性的交通标志和人脸识别应用程序的背景下证明。他们每个人都暴露在不同的攻击与各种触发器。结果表明,该方法在所有测试攻击中将攻击成功率显着降低到< 1%,同时在处理良性和敌对数据时保持并提高了模型的初始准确性。

英文摘要:

Deep Neural Networks (DNNs) have been applied successfully in computer vision. However, their wide adoption in image-related applications is threatened by their vulnerability to trojan attacks. These attacks insert some misbehavior at training using samples with a mark or trigger, which is exploited at inference or testing time. In this work, we analyze the composition of the features learned by DNNs at training. We identify that they, including those related to the inserted triggers, contain both content (semantic information) and style (texture information), which are recognized as a whole by DNNs at testing time. We then propose a novel defensive technique against trojan attacks, in which DNNs are taught to disregard the styles of inputs and focus on their content only to mitigate the effect of triggers during the classification. The generic applicability of the approach is demonstrated in the context of a traffic sign and a face recognition application. Each of them is exposed to a different attack with a variety of triggers. Results show that the method reduces the attack success rate significantly to values < 1% in all the tested attacks while keeping as well as improving the initial accuracy of the models when processing both benign and adversarial data.

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。

↑