Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples
In this paper, we introduce the idea of using adversarially-generated samples of the input images that were classified as deepfakes by a detector, to form perturbation masks for inferring the importance of different input features and produce visual explanations. We generate these samples based on Natural Evolution Strategies, aiming to flip the original deepfake detector's decision and classify these samples as real. We apply this idea to four perturbation-based explanation methods (LIME, SHAP, SOBOL and RISE) and evaluate the performance of the resulting modified methods using a SOTA deepfake detection model, a benchmarking dataset (FaceForensics++) and a corresponding explanation evaluation framework. Our quantitative assessments document the mostly positive contribution of the proposed perturbation approach in the performance of explanation methods. Our qualitative analysis shows the capacity of the modified explanation methods to demarcate the manipulated image regions more accurately, and thus to provide more useful explanations.
Code (2)
Tasks
BenchmarkingDeepFake DetectionFace SwappingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before. Manipulated videos can fuel disinformation and reduce trust in media. Therefore detection of fake…
DeepFake DetectionFace SwappingVideo CompressionAdversarial Perturbations Fool Deepfake Detectors
This work uses adversarial perturbations to enhance deepfake images and fool common deepfake detectors. We created adversarial perturbations using the Fast Gradient Sign Method and the Carlini and Wagner L2 norm attack i…
Face SwappingAdversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning
Deepfake technology has raised concerns about the authenticity of digital content, necessitating the development of effective detection methods. However, the widespread availability of deepfakes has given rise to a new c…
DeepFake DetectionFace SwappingDeepFake Disrupter: The Detector of DeepFake Is My Friend
In recent years, with the advances of generative models, many powerful face manipulation systems have been developed based on Deep Neural Networks (DNNs), called DeepFakes. If DeepFakes are not controlled timely and …
Face SwappingQuantitative Metrics for Evaluating Explanations of Video DeepFake Detectors
The proliferation of DeepFake technology is a rising challenge in today's society, owing to more powerful and accessible generation methods. To counter this, the research community has developed detectors of ever-increas…
AttributeFace SwappingInformativeness