Zhongjie Ba

The paper proposes W-IR, a novel watermarking framework that simultaneously achieves high certified robustness against adversarial attacks and effectively mitigates identity leakage in watermarked images.

The paper introduces ToxiAlert-Bench, a large-scale audio dataset that uniquely annotates both textual and paralinguistic sources of toxicity, and proposes a dual-head neural network that significantly improves speech toxicity detection by leveraging these paralinguistic cues.