3 papers
cs.CL2021
BFClass: A Backdoor-free Text Classification Framework
Zichao Li, Dheeraj Mekala, Chengyu Dong +1
Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design…
cs.LG2021
Data Quality Matters For Adversarial Training: An Empirical Study
Chengyu Dong, Liyuan Liu, Jingbo Shang
Multiple intriguing problems are hovering in adversarial training, including robust overfitting, robustness overestimation, and robustness-accuracy trade-off. These problems pose g…
cs.LG2020
Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training
Zichao Li, Liyuan Liu, Chengyu Dong +1
Our goal is to understand why the robustness drops after conducting adversarial training for too long. Although this phenomenon is commonly explained as overfitting, our analysis s…