paper-with-me

홈 › Papers

Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View

2023-01-01 · ICCV 2023 1 · Kelu Yao, Jin Wang, Boyu Diao, Chao Li

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DeepFake DetectionFace Swapping

Similar Papers 제목 키워드 기반

DFGC 2021: A DeepFake Game Competition

2021-06-02 · Bo Peng, Hongxing Fan, Wei Wang, Jing Dong 외

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 Swapping

Deepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns Injection

2024-03-20 · Davide Alessandro Coccomini, Roberto Caldelli, Claudio Gennaro, Giuseppe Fiameni 외

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 Generation

DFGC-VRA: DeepFake Game Competition on Visual Realism Assessment

2023-09-01 · journal 2023 9 · Bo Peng, Xianyun Sun, Caiyong Wang, Wei Wang1 외

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 Swapping

Decoupling Forgery Semantics for Generalizable Deepfake Detection

2024-06-14 · Wei Ye, Xinan He, Feng Ding

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 Swapping

SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Framework

2024-01-09 · Binh M. Le, Jiwon Kim, Simon S. Woo, Kristen Moore 외

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