5 papers
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders
Xinghao Wang, Dong Li, Wei Yu +5
Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative capabilities, yet their reliance on loosely curated training data raises pressing sa…
TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images
Yuning Zhang, Changtao Miao, Mingyu Liao +5
Recent AI-generated image (AIGI) detectors perform well on natural-image benchmarks, but their behavior on text-rich forgeries, such as fabricated screenshots, documents, and news…
SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization
Xinghao Wang, Changtao Miao, Dianmo Sheng +6
Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training e…
Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization
Rui Chen, Bin Liu, Changtao Miao +5
Advances in image tampering pose serious security threats, underscoring the need for effective image manipulation localization (IML). While supervised IML achieves strong performan…
Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement
Xinghao Wang, Tao Gong, Qi Chu +2
Malicious image manipulation poses societal risks, increasing the importance of effective image manipulation detection methods. Recent approaches in image manipulation detection ha…