Bilkent University
Department of Computer Engineering
M.S.THESIS PRESENTATION
Generalizable Face Forgery Detection with Metric Learning And Domain-adversarial Training
Mustafa Hakan Kara
Master Student
(Supervisor: Prof.Dr.Uğur Güdükbay)
(Co-Advisor: Asst.Prof.Ayşegül Dündar Boral)
Computer Engineering Department
Bilkent University
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 based on supervised training with 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 with a Siamese network architecture for enhanced 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 towards forgery-agnostic representations, improving its robustness to unseen manipulations. In addition, we prevent gradient flow from the classifier head to the embedding model, avoiding overfitting to artifacts peculiar to certain forgeries. Comprehensive evaluations across multiple benchmarks and ablation studies demonstrate the effectiveness of our framework.
DATE: April 08, Monday @ 15:30 Place: EA 409