Back to AI News
arxiv

MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection

Researchers introduce MARS, a two-path video detector that combines multiscale feature differences with appearance representations to improve deepfake detection across facial manipulations and fully generated videos. The method achieves the highest average AUROC of 91.43% across seven datasets, outperforming seven compared detectors. It also shows strong transfer to generated videos when trained only on facial manipulations, and provides interpretable patch and frame contributions.

AI Brief

This paper presents a novel, state-of-the-art approach to video forgery detection with strong benchmark results and public code, offering practical value for AI security and media forensics.

arXiv:2611.12508v1 Announce Type: cross Abstract: Generalizing deepfake detection across facial manipulation and fully generated video remains challenging due to forgery traces varying with the manipulation method and scene content. Explicit spatial and temporal feature differences offer a way to capture this variation, but also respond to natural texture and motion, motivating their joint interpretation with appearance features. We investigate whether combining multiscale feature differences with adapted appearance representations improves detection across both forgery categories. We introduce Multiscale Appearance-Residual Streams (MARS), a two-path video detector. The residual path applies fixed spatial and temporal difference-of-Gaussians operators to frozen intermediate features and models the resulting differences alongside appearance context across frames. The semantic path adapts the encoder's normalization parameters for frame classification, and a clip-dependent gate combines their predictions. Under a shared protocol across seven datasets, MARS achieves the highest average AUROC of 91.43\%, outperforming seven compared detectors. When trained on facial manipulations alone, MARS achieves 93.99\% AUROC on GenVideo and 75.50\% on DF26, demonstrating transfer to generated videos without generated-video training data. MARS also provides signed patch and frame contributions, whose faithfulness we evaluate through controlled spatial and temporal removal against random controls. MARS is publicly available for research: Project page: https://vectorinstitute.github.io/mars/ Github: https://github.com/VectorInstitute/mars
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!