Trident: Detecting Face Forgeries With Domain-Adversarial Triplet Learning

Abstract

As face forgeries generated by deep neural networks become increasingly sophisticated, detecting face manipulations in digital media has posed a significant challenge, underscoring the importance of maintaining digital media integrity and combating visual disinformation. Current detection models, predominantly trained on domain-specific data, often falter against forgeries generated by unencountered techniques. In response to this challenge, we introduce Trident, a face forgery detection framework that employs triplet learning within a Siamese network architecture to enhance adaptability across diverse forgery methods. Trident is trained on curated triplets to isolate nuanced differences of forgeries, capturing fine-grained features that distinguish pristine samples from manipulated ones while controlling for other variables. To further enhance generalizability, we incorporate domain-adversarial training with a forgery discriminator. This adversarial component guides our embedding model toward forgery-agnostic representations, improving its robustness to unseen manipulations. In addition, we prevent gradient flow from the classifier head to the embedding model, thereby avoiding overfitting induced by artifacts specific to certain forgeries. Comprehensive evaluations across multiple benchmarks and ablation studies demonstrate the effectiveness of our framework.