7 papers
MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
Xiaoxi Kong, Jieyu Yuan, Pengdi Chen +3
Semantic watermarks exhibit strong robustness against conventional image-space attacks. In this work, we show that such robustness does not survive under micro-geometric perturbati…
MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations
Xinan He, Kaiqing Lin, Yue Zhou +8
With the rapid advancement of video generation models such as Veo and Wan, the visual quality of synthetic content has reached a level where macro-level semantic errors and tempora…
Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detection
Yue Zhou, Xinan He, Kaiqing Lin +4
While specialized detectors for AI-generated images excel on curated benchmarks, they fail catastrophically in real-world scenarios, as evidenced by their critically high false-neg…
Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images
Chuangchuang Tan, Xiang Ming, Jinglu Wang +5
The rapid advancement of AI-generated content (AIGC) has enabled the synthesis of visually convincing images; however, many such outputs exhibit subtle \textbf{semantic anomalies},…
Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation
Chenfan Qu, Yiwu Zhong, Huiguo He +2
Images manipulated by image editing tools can mislead viewers and pose significant risks to social security. However, accurately localizing manipulated image regions remains challe…
Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection
Yue Zhou, Xinan He, KaiQing Lin +3
Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators.…