Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts

arXiv:2404.08341v1 Announce Type: new
Abstract: Highly realistic AI generated face forgeries known as deepfakes have raised serious social concerns. Although DNN-based face forgery detection models have achieved good performance, they are vulnerable to latest generative methods that have less forgery traces and adversarial attacks. This limitation of generalization and robustness hinders the credibility of detection results and requires more explanations. In this work, we provide counterfactual explanations for face forgery detection from an artifact removal perspective. Specifically, we first invert …

abstract adversarial adversarial attacks ai generated arxiv attacks concerns counterfactual cs.cv deepfakes detection dnn face forgery generated generative good performance social traces type via vulnerable