Defending against high-poisoning backdoor attacks by exploiting loss divergence

Information Fusion 2026

View at publisher

Authors: Yuzhuo Jin, Ruijin Wang, Na Wang, Donglin He, Yang Zhang, Zhiquan Liu

DOI: 10.1016/j.inffus.2026.104308

Cited by: 1

References: 10

Fields of Study & Subjects

Adversarial Robustness in Machine Learning Cryptographic Implementations and Security Network Security and Intrusion Detection

References 10