4 papers
Chameleon: Benchmarking Detection and Backtracking on Commercial-Grade AI-Generated Videos
Xingming Liao, Meiyu Zeng, Canyu Chen +3
The proliferation of AI-Generated Content (AIGC), especially deepfake videos, poses a severe threat to social trust by enabling fraud, privacy violations and disinformation. Existi…
HateDebias: On the Diversity and Variability of Hate Speech Debiasing
Hongyan Wu, Zhengming Chen, Zijian Li +4
Hate speech frequently appears on social media platforms and urgently needs to be effectively controlled. Alleviating the bias caused by hate speech can help resolve various ethica…
CLASS: Enhancing Cross-Modal Text-Molecule Retrieval Performance and Training Efficiency
Hongyan Wu, Peijian Zeng, Weixiong Zheng +4
Cross-modal text-molecule retrieval task bridges molecule structures and natural language descriptions. Existing methods predominantly focus on aligning text modality and molecule…
Jailbreaking? One Step Is Enough!
Weixiong Zheng, Peijian Zeng, Yiwei Li +5
Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbrea…