2 papers
cs.AI2026
AdaGuard: An Adaptive Guard Model with User-defined Policies
Yunhao Feng, Yifan Ding, Yuxiang Xie +4
Guard models support the safe deployment of language model agents, but fixed risk taxonomies limit their ability to accommodate requirements that vary across applications and tasks…
cs.LG2025
Learning from Peers: Collaborative Ensemble Adversarial Training
Li Dengjin, Guo Yanming, Xie Yuxiang +4
Ensemble Adversarial Training (EAT) attempts to enhance the robustness of models against adversarial attacks by leveraging multiple models. However, current EAT strategies tend to…