CalF AT: Calibrated Federated Adversarial Training with Label Skewness Chen Chen Zhejiang University Y uchen Liu Zhejiang University Xingjun Ma Fudan University Lingjuan Lyu Sony AI

Oct-2-2025, 14:51:58 GMT–Neural Information Processing Systems 

Recent studies have shown that, like traditional machine learning, federated learning (FL) is also vulnerable to adversarial attacks.