{"ID":2877636,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00089","arxiv_id":"2509.00089","title":"Learning from Peers: Collaborative Ensemble Adversarial Training","abstract":"Ensemble Adversarial Training (EAT) attempts to enhance the robustness of models against adversarial attacks by leveraging multiple models. However, current EAT strategies tend to train the sub-models independently, ignoring the cooperative benefits between sub-models. Through detailed inspections of the process of EAT, we find that that samples with classification disparities between sub-models are close to the decision boundary of ensemble, exerting greater influence on the robustness of ensemble. To this end, we propose a novel yet efficient Collaborative Ensemble Adversarial Training (CEAT), to highlight the cooperative learning among sub-models in the ensemble. To be specific, samples with larger predictive disparities between the sub-models will receive greater attention during the adversarial training of the other sub-models. CEAT leverages the probability disparities to adaptively assign weights to different samples, by incorporating a calibrating distance regularization. Extensive experiments on widely-adopted datasets show that our proposed method achieves the state-of-the-art performance over competitive EAT methods. It is noteworthy that CEAT is model-agnostic, which can be seamlessly adapted into various ensemble methods with flexible applicability.","short_abstract":"Ensemble Adversarial Training (EAT) attempts to enhance the robustness of models against adversarial attacks by leveraging multiple models. However, current EAT strategies tend to train the sub-models independently, ignoring the cooperative benefits between sub-models. Through detailed inspections of the process of EAT...","url_abs":"https://arxiv.org/abs/2509.00089","url_pdf":"https://arxiv.org/pdf/2509.00089v1","authors":"[\"Li Dengjin\",\"Guo Yanming\",\"Xie Yuxiang\",\"Li Zheng\",\"Chen Jiangming\",\"Li Xiaolong\",\"Lao Mingrui\"]","published":"2025-08-27T13:10:40Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}