Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs has gained considerable interest in recent years. Although image transformation-based defenses were widely considered at an earlier time, most of them have been defeated by adaptive attacks. In this paper, we propose a new image transformation defense based on error diffusion halftoning, and combine it with adversarial training to defend against adversarial examples. Error diffusion halftoning projects an image into a 1-bit space and diffuses quantization error to neighboring pixels. This process can remove adversarial perturbations from a given image while maintaining acceptable image quality in the meantime in favor of recognition. Experimental results demonstrate that the proposed method is able to improve adversarial robustness even under advanced adaptive attacks, while most of the other image transformation-based defenses do not. We show that a proper image transformation can still be an effective defense approach. Code: https://github.com/shaoyuanlo/Halftoning-Defense
翻译:Aversarial 示例中包含精心设计的扰动模型,可以愚弄深神经网络(DNNS),做出错误的预测。加强DNN的对抗性强力近年来引起了相当大的兴趣。虽然图像转换防御在早期曾得到广泛考虑,但大多数都因适应性攻击而失败。在本文中,我们提出基于错误扩散半颗粒的新图像转换防御,并结合对抗对抗性例子的对抗性训练。错误将图像的半颗粒子投射成一位空间,向相邻像素扩散定量错误。这一过程可以从给定图像中去除对抗性扰动,同时保持可接受的图像质量,同时支持认知。实验结果表明,即使在先进的适应性攻击下,拟议方法也能提高对抗性强力,而其他大多数基于图像转换的防御则并不成功。我们表明,适当的图像转换仍可能是有效的防御方法。代码: https://github.com/shaoyuanlo/Halftoning-Defense。