Security of Facial Forensics Models Against Adversarial Attacks

Deep neural networks (DNNs) have been used in forensics to identify fake facial images. We investigated several DNN-based forgery forensics models (FFMs) to determine whether they are secure against adversarial attacks. We experimentally demonstrated the existence of individual adversarial perturbations (IAPs) and universal adversarial perturbations (UAPs) that can lead a well-performed FFM to misbehave. Based on iterative procedure, gradient information is used to generate two kinds of IAPs that can be used to fabricate classification and segmentation outputs. In contrast, UAPs are generated on the basis of over-firing. We designed a new objective function that encourages neurons to over-fire, which makes UAP generation feasible even without using training data. Experiments demonstrated the transferability of UAPs across unseen datasets and unseen FFMs. Moreover, we are the first to conduct subjective assessment for imperceptibility of the adversarial perturbations, revealing that the crafted UAPs are visually negligible. There findings provide a baseline for evaluating the adversarial security of FFMs.