Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View
This paper aims to explain the generalization of deepfake detectors from the novel perspective of multi-order interactions among visual concepts. Specifically, we propose three hypotheses: 1. Deepfake detectors encode multi-order interactions among visual concepts, in which the low-order interactions usually have substantially negative contributions to deepfake detection. 2. Deepfake detectors with better generalization abilities tend to encode low-order interactions with fewer negative contributions. 3. Generalized deepfake detectors usually weaken the negative contributions of low-order interactions by suppressing their strength. Accordingly, we design several mathematical metrics to evaluate the effect of low-order interaction for deepfake detectors. Extensive comparative experiments are conducted, which verify the soundness of our hypotheses. Based on the analyses, we further propose a generic method, which directly reduces the toxic effects of low-order interactions to improve the generalization of deepfake detectors to some extent. The code will be released when the paper is accepted.
Code (0)
등록된 구현이 없습니다.
Tasks
DeepFake DetectionFace SwappingSimilar Papers 제목 키워드 기반
DFGC 2021: A DeepFake Game Competition
This paper presents a summary of the DFGC 2021 competition. DeepFake technology is developing fast, and realistic face-swaps are increasingly deceiving and hard to detect. At the same time, DeepFake detection methods are…
BenchmarkingDeepFake DetectionFace SwappingDeepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns Injection
Deepfake detectors are typically trained on large sets of pristine and generated images, resulting in limited generalization capacity; they excel at identifying deepfakes created through methods encountered during traini…
DeepFake DetectionFace SwappingImage GenerationDFGC-VRA: DeepFake Game Competition on Visual Realism Assessment
This paper presents the summary report on the DeepFake Game Competition on Visual Realism Assessment (DFGCVRA). Deep-learning based face-swap videos, also known as deepfakes, are becoming more and more realistic and dec…
Face SwappingDecoupling Forgery Semantics for Generalizable Deepfake Detection
In this paper, we propose a novel method for detecting DeepFakes, enhancing the generalization of detection through semantic decoupling. There are now multiple DeepFake forgery technologies that not only possess unique f…
DeepFake DetectionFace SwappingSoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Framework
Deepfakes have rapidly emerged as a serious threat to society due to their ease of creation and dissemination, triggering the accelerated development of detection technologies. However, many existing detectors rely on la…
BenchmarkingDeepFake DetectionFace Swapping