3 papers
cs.SD2026
Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
Zhongjie Ba, Liang Yi, Peng Cheng +3
Toxic speech detection has become a crucial challenge in maintaining safe online communication environments. However, existing approaches to toxic speech detection often neglect th…
cs.CR2025
WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
Ziping Dong, Chao Shuai, Zhongjie Ba +4
Invisible Image Watermarking is crucial for ensuring content provenance and accountability in generative AI. While Gen-AI providers are increasingly integrating invisible watermark…
cs.CV2025
Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
Zhongjie Ba, Yitao Zhang, Peng Cheng +4
Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compr…