Weibo Xu

CDO-GIA: A Robust Textual Gradient Inversion Attack Against Federated Language Models via Continuous-Discrete Optimization

Gradient inversion attacks (GIAs) have shown that shared gradients in federated learning leak private training data. However, current textual GIAs fail in large batch size, as simply increasing batch size can serve as a stable defense against such attacks. In this paper, we propose CDO-GIA, a novel