3 papers
cs.CV2025
Rethinking Cross-Generator Image Forgery Detection through DINOv3
Zhenglin Huang, Jason Li, Haiquan Wen +7
As generative models become increasingly diverse and powerful, cross-generator detection has emerged as a new challenge. Existing detection methods often memorize artifacts of spec…
cs.CV2025
So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection
Zhenglin Huang, Xiangtai Li, Xi Yang +6
Recent advances in AI-powered generative models have enabled the creation of increasingly realistic synthetic images, posing significant risks to information integrity and public t…
cs.CV2023
IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers
Zhenglin Huang, Xiaoan Bao, Na Zhang +4
Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in…