Jiaran Zhou — accepted AI-conference papers

2025

Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection

Xinjie Cui, Yuezun Li, Ao Luo, Jiaran Zhou, Junyu Dong

CVPR 2025poster

We describe the Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting it for face forgery detection is non-trivial as forgery-related knowledge is entangled with a wide range of unrelate…

Cited by 5 Source ↗PDF ↗Scholar ↗

2024

FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge

Hanzhe LI, Jiaran Zhou, Yuezun Li, Baoyuan Wu, Bin Li, Junyu Dong

NeurIPS 2024poster

Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation…

Cited by 8 Source ↗PDF ↗Scholar ↗