2 papers
cs.LG2026
APEX: Probing Neural Networks via Activation Perturbation
Tao Ren, Xiaoyu Luo, Qiongxiu Li
Prior work on probing neural networks primarily relies on input-space analysis or parameter perturbation, both of which face fundamental limitations in accessing structural informa…
cs.CR2024
ProP: Efficient Backdoor Detection via Propagation Perturbation for Overparametrized Models
Tao Ren, Qiongxiu Li
Backdoor attacks pose significant challenges to the security of machine learning models, particularly for overparameterized models like deep neural networks. In this paper, we prop…