Open Set Face Forgery Detection via Dual-Level Evidence Collection

2025-12-03

AI Summary

This work addresses open-set face forgery detection (OSFFD)—the challenge of identifying previously unseen forgery types when the model is trained exclusively on known forgery categories. We propose a novel two-level evidence fusion framework grounded in uncertainty modeling, marking the first application of evidential deep learning to OSFFD. Our method integrates spatial- and frequency-domain feature extraction within a unified architecture, enabling joint perception and discrimination of both known and unknown forgery classes. Crucially, it operates without prior knowledge of unknown categories. Under multiple open-set evaluation protocols, our approach achieves an average 20% improvement in detection accuracy over state-of-the-art baselines, while maintaining competitive performance on standard binary real/fake classification. This demonstrates significantly enhanced generalization and robustness in dynamic, real-world adversarial environments.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The proliferation of face forgeries has increasingly undermined confidence in the authenticity of online content. Given the rapid development of face forgery generation algorithms, new fake categories are likely to keep appearing, posing a major challenge to existing face forgery detection methods. Despite recent advances in face forgery detection, existing methods are typically limited to binary Real-vs-Fake classification or the identification of known fake categories, and are incapable of detecting the emergence of novel types of forgeries. In this work, we study the Open Set Face Forgery Detection (OSFFD) problem, which demands that the detection model recognize novel fake categories. We reformulate the OSFFD problem and address it through uncertainty estimation, enhancing its applicability to real-world scenarios. Specifically, we propose the Dual-Level Evidential face forgery Detection (DLED) approach, which collects and fuses category-specific evidence on the spatial and frequency levels to estimate prediction uncertainty. Extensive evaluations conducted across diverse experimental settings demonstrate that the proposed DLED method achieves state-of-the-art performance, outperforming various baseline models by an average of 20% in detecting forgeries from novel fake categories. Moreover, on the traditional Real-versus-Fake face forgery detection task, our DLED method concurrently exhibits competitive performance.

Problem

• Detects novel fake face categories in open-set scenarios
• Uses dual-level evidence fusion for uncertainty estimation
• Improves detection of unknown forgeries by 20% over baselines

Innovation

• Dual-level evidence collection for uncertainty estimation
• Spatial and frequency level evidence fusion
• Open set detection for novel fake categories