Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts | |
Li, Yang1,2; Yang, Songlin1,2![]() ![]() ![]() ![]() | |
2024-06 | |
会议名称 | IEEE International Conference on Multimedia and Expo (ICME) |
会议日期 | 2024-6 |
会议地点 | Niagara Falls, Canada |
摘要 | 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 the forgery images into the StyleGAN latent space, and then adversarially optimize their latent representations with the discrimination supervision from the target detection model. We verify the effectiveness of the proposed explanations from two aspects: (1) Counterfactual Trace Visualization: the enhanced forgery images are useful to reveal artifacts by visually contrasting the original images and two different visualization methods; (2) Transferable Adversarial Attacks: the adversarial forgery images generated by attacking the detection model are able to mislead other detection models, implying the removed artifacts are general. Extensive experiments demonstrate that our method achieves over 90% attack success rate and superior attack transferability. Compared with naive adversarial noise methods, our method adopts both generative and discriminative model priors, and optimize the latent representations in a synthesis-by-analysis way, which forces the search of counterfactual explanations on the natural face manifold. Thus, more general counterfactual traces can be found and better adversarial attack transferability can be achieved. |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57552 |
专题 | 模式识别实验室 |
通讯作者 | Wang, Wei |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, China 2.CRIPAC, MAIS, Institute of Automation, Chinese Academy of Sciences, China 3.}Nanjing University of Information Science and Technology, China 4.School of Artificial Intelligence, University of Chinese Academy of Sciences, China 5.CRIPAC, MAIS, Institute of Automation, Chinese Academy of Sciences, China 6.}Nanjing University of Information Science and Technology, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li, Yang,Yang, Songlin,Wang, Wei,et al. Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts[C],2024. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ICME_2024_PAPER.pdf(7605KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论