arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.05151cs.CV
收藏

基于频率驱动的语义相似度不可感知对抗攻击

Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity

Shenzhen University(深圳大学)

Cheng Luo, Qinliang Lin, Weicheng Xie, Bizhu Wu, Jinheng Xie, Linlin Shen

摘要:

当前的对抗攻击研究揭示了基于学习的分类器在面对精心设计的扰动时的脆弱性。然而,大多数现有的攻击方法在跨数据集泛化方面具有固有的局限性,因为它们依赖于具有封闭类别集的分类层。此外,这些方法产生的扰动可能出现在人类视觉系统(HVS)容易感知的区域。为了规避前一个问题,我们提出了一种新的算法,攻击特征表示的语义相似性。通过这种方式,我们能够欺骗分类器,而不会将攻击限制在特定的数据集上。对于不可感知性,我们引入低频约束来限制高频分量内的扰动,确保对抗性示例和原始示例之间的感知相似性。在三个数据集(CIFAR-10,CIFAR-100和ImageNet-1 K)和三个公共在线平台上进行的广泛实验表明,我们的攻击可以在架构和数据集之间产生误导性和可转移的对抗性示例。此外,可视化结果和定量性能(在四个不同的度量方面)表明,该算法比最先进的方法产生更多的不可察觉的扰动。代码可在。

英文摘要:

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they rely on a classification layer with a closed set of categories. Furthermore, the perturbations generated by these methods may appear in regions easily perceptible to the human visual system (HVS). To circumvent the former problem, we propose a novel algorithm that attacks semantic similarity on feature representations. In this way, we are able to fool classifiers without limiting attacks to a specific dataset. For imperceptibility, we introduce the low-frequency constraint to limit perturbations within high-frequency components, ensuring perceptual similarity between adversarial examples and originals. Extensive experiments on three datasets (CIFAR-10, CIFAR-100, and ImageNet-1K) and three public online platforms indicate that our attack can yield misleading and transferable adversarial examples across architectures and datasets. Additionally, visualization results and quantitative performance (in terms of four different metrics) show that the proposed algorithm generates more imperceptible perturbations than the state-of-the-art methods. Code is made available at.

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。

↑