RTRGAN: Ridge Texture Rendering Based Generative Adversarial Fingerprint Attack for Portable Consumer Electronics Devices

Deep Fake Fingerprint Detection (DFFD) technique is ubiquitously deployed in automatic fingerprint identification systems (AFIS). Portable consumer electronics devices (PCED), such as smartphones, smart tablets, and PCs, also utilize fingerprint as a authentication method of AFIS. In recent years, the emergence of adversarial examples reveals the vulnerability of DNNs and weakens the credibility of PCED. Existing adversarial examples generally adopt perturbation addition, which lack robustness in the face of defensive measures such as adversarial training. Moreover, the perturbations used to deceive DFFD are easily perceived by human eyes. To address the above challenges, this paper proposes a novel generative adversarial fingerprint attack method for PCED. Firstly, to address the issue of poor robustness against defense strategies, this paper proposes a ridge texture rendering based generative adversarial network (RTRGAN) to perform robust generative adversarial fingerprint attack. Subsequently, to further enhance the visual quality of adversarial fingerprints, the realistic ridge texture is assigned by comparing the feature similarity between real fingerprints and adversarial fingerprints. Finally, this paper designs a joint optimization loss function, including the discriminator loss and the adversarial loss, to balance the attack robustness and visual fidelity. Extensive experiments demonstrate that compared with traditional perturbation-based methods, the proposed scheme significantly improves the attack success rate, has remarkable robustness, and generates more realistic adversarial fingerprints to human perception.