Towards Undetectable Adversarial Examples: A Steganographic Perspective

Hui Zeng, Biwei Chen, Rongsong Yang, Chenggang Li, Anjie Peng

Abstract: Over the past decade, adversarial examples have demonstrated an enhancing ability to fool neural networks. However, most adversarial examples can be easily detected, especially under statistical analysis. Ensuring undetectability is crucial for the success of adversarial examples in practice. In this paper, we borrow the idea of the embedding suitability map from steganography and employ it to modulate the adversarial perturbation. In this way, the adversarial perturbations are concentrated in the hard-to-detect areas and are attenuated in predictable regions. Extensive experiments show that the proposed scheme is compatible with various existing attacks and can significantly boost the undetectability of adversarial examples against both human inspection and statistical analysis of the same attack ability. The code is available at github.com/zengh5/Undetectable-attack.