1 code implementation • 29 Jan 2024 • Hao Wang, Tao Xiang, Shangwei Guo, Jialing He, Hangcheng Liu, Tianwei Zhang
Adopting untrusted PTMs may suffer from backdoor attacks, where the adversary can compromise the downstream models by injecting backdoors into the PTM.
no code implementations • 4 Jan 2021 • Tao Xiang, Hangcheng Liu, Shangwei Guo, Tianwei Zhang, Xiaofeng Liao
Based on this property, we identify the discriminative areas of a given clean example easily for local perturbations.