Distortion-aware adversarial attack against steganalysis detectors

Abstract

This paper analyzes the similarity between steganography and adversarial attack, and then analyzes the attack and defense stage of adversarial samples from the perspective of steganography, which provides a broader idea for researchers in this field. This paper validates the efficiency of steganography on help resisting adversarial attack and proposes a steganalysis based method to enhance the adversarial attack against steganalysis detectors with the help of a distortion function. We combine the distortion map with gradient information to select the disturbed pixels in each attack iteration to generate adversarial samples that can bypass steganalysis detectors. The results show that steganography technology can help detecting normal adversarial samples, and our enhanced adversarial samples achieve a much higher transparency rate against our steganography based method than other normal adversarial samples.