In black-box adversarial attacks, adversaries query the deep neural network (DNN), use the output to reconstruct gradients, and then optimize the adversarial inputs iteratively. In this paper, we study the method of adding white noise to the DNN output to mitigate such attacks, with a unique focus on the trade-off analysis of noise level and query cost. The attacker's query count (QC) is derived mathematically as a function of noise standard deviation. With this result, the defender can conveniently find the noise level needed to mitigate attacks for the desired security level specified by QC and limited DNN performance loss. Our analysis shows that the added noise is drastically magnified by the small variation of DNN outputs, which makes the reconstructed gradient have an extremely low signal-to-noise ratio (SNR). Adding slight white noise with a standard deviation less than 0.01 is enough to increase QC by many orders of magnitude without introducing any noticeable classification accuracy reduction. Our experiments demonstrate that this method can effectively mitigate both soft-label and hard-label black-box attacks under realistic QC constraints. We also show that this method outperforms many other defense methods and is robust to the attacker's countermeasures.
翻译:在黑盒对抗性攻击中,对手会询问深神经网络(DNN),使用输出来重建梯度,然后优化对抗性输入。在本文中,我们研究在 DNN 输出中添加白噪音的方法,以减轻这种攻击,特别侧重于对噪音水平和查询成本的权衡分析。攻击者的查询数(QC)是数学上得出的,因为噪音标准偏差的函数。因此,捍卫者可以方便地找到所需的噪音水平,以缓解QC 和有限的DNN 性能损失所要求安全水平的攻击。我们的分析表明,DNN 输出的微小变异大大放大了增加的噪音,使重建的梯度的信号对噪音比率极低。加上标准偏差小于0.01的微白噪音,足以使QC增加许多数量级的量,而不会带来明显的分类准确性降低。我们的实验表明,这种方法可以在现实的QC限制下有效地减轻软标签和硬标签黑箱攻击。我们还表明,这种方法超越了其他防御措施。