arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09774cs.CVcs.AI
收藏

用单个图像生成对抗性但不显眼的补丁

Generating Adversarial yet Inconspicuous Patches with a Single Image

Nanyang Technological University(南洋理工大学)

Jinqi Luo, Tao Bai, Jun Zhao

摘要:

深度神经网络已经被证明容易受到对抗补丁的攻击,其中外来模式可能导致模型错误预测。然而,现有的对抗性补丁生成方法很少考虑补丁与图像背景之间的上下文一致性,导致这种补丁很容易被检测到,从而导致对抗攻击失败。另一方面,这些方法需要大量的数据进行训练,这在计算上是昂贵的。为了克服这些挑战,我们提出了一种方法来生成对抗性但不显眼的补丁与一个单一的图像。在我们的方法中,对抗补丁是以一种由粗到细的方式产生的,具有多个尺度的生成器和鉴别器。在Min-Max训练过程中对上下文信息进行编码,以使匹配与环境一致。补丁位置的选择是基于受害者模型的感知灵敏度。通过大量的实验,我们的方法显示出强大的攻击能力,在白盒和黑盒设置。显著性检测实验和用户评价实验表明,该方法能有效地避免人工观察,具有较好的隐蔽性。最后,我们证明了我们的方法保留了物理世界中的攻击能力。

英文摘要:

Deep neural networks have been shown vulnerable toadversarial patches, where exotic patterns can resultin models wrong prediction. Nevertheless, existing ap-proaches to adversarial patch generation hardly con-sider the contextual consistency between patches andthe image background, causing such patches to be eas-ily detected and adversarial attacks to fail. On the otherhand, these methods require a large amount of data fortraining, which is computationally expensive. To over-come these challenges, we propose an approach to gen-erate adversarial yet inconspicuous patches with onesingle image. In our approach, adversarial patches areproduced in a coarse-to-fine way with multiple scalesof generators and discriminators. Contextual informa-tion is encoded during the Min-Max training to makepatches consistent with surroundings. The selection ofpatch location is based on the perceptual sensitivity ofvictim models. Through extensive experiments, our ap-proach shows strong attacking ability in both the white-box and black-box setting. Experiments on saliency de-tection and user evaluation indicate that our adversar-ial patches can evade human observations, demonstratethe inconspicuousness of our approach. Lastly, we showthat our approach preserves the attack ability in thephysical world.

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。

↑