Unmasking the Unknown: Facial Deepfake Detection in the Open-Set Paradigm

2025-03-11

AI Summary

Generative AI has enabled novel, previously unseen deepfake face generation methods, rendering conventional closed-set detection inadequate—existing models often misclassify such unknown forgeries as authentic. Method: This paper pioneers open-set learning for deepfake detection, formally defining and modeling an “unknown forgery” class to enable active rejection—not misclassification—of unseen manipulation techniques. We propose a supervised contrastive learning framework that jointly enforces feature-space separation among known classes and explicitly models the decision boundary for the unknown class. Results: On FaceForensics++, our method achieves state-of-the-art performance in open-set detection—simultaneously rejecting unknown forgeries and correctly classifying known real/forged samples—without compromising accuracy on known forgery types. Our core contribution is the first systematic formulation of open-set deepfake detection targeting unknown forgeries, accompanied by a theoretically grounded, scalable modeling approach and efficient implementation.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Facial forgery methods such as deepfakes can be misused for identity manipulation and spreading misinformation. They have evolved alongside advancements in generative AI, leading to new and more sophisticated forgery techniques that diverge from existing 'known' methods. Conventional deepfake detection methods use the closedset paradigm, thus limiting their applicability to detecting forgeries created using methods that are not part of the training dataset. In this paper, we propose a shift from the closed-set paradigm for deepfake detection. In the open-set paradigm, models are designed not only to identify images created by known facial forgery methods but also to identify and flag those produced by previously unknown methods as 'unknown' and not as unforged/real/unmanipulated. In this paper, we propose an open-set deepfake classification algorithm based on supervised contrastive learning. The open-set paradigm used in our model allows it to function as a more robust tool capable of handling emerging and unseen deepfake techniques, enhancing reliability and confidence, and complementing forensic analysis. In open-set paradigm, we identify three groups including the"unknown group that is neither considered known deepfake nor real. We investigate deepfake open-set classification across three scenarios, classifying deepfakes from unknown methods not as real, distinguishing real images from deepfakes, and classifying deepfakes from known methods, using the FaceForensics++ dataset as a benchmark. Our method achieves state of the art results in the first two tasks and competitive results in the third task.

Problem

• Detects deepfakes from unknown forgery methods.
• Shifts from closed-set to open-set detection paradigm.
• Enhances reliability in identifying emerging deepfake techniques.

Innovation

• Open-set paradigm for deepfake detection
• Supervised contrastive learning algorithm
• Handles unknown deepfake techniques effectively