← Search

Bao-di Liu

2 accepted papers

2025

Disentangled Information Bottleneck for Adversarial Text Defense

EMNLP 2025

Adversarial text defense is a significant strategy to protect modern NLP models from being attacked. Typical text defense methods usually enhance the model’s robustness by model retraining or equipping it with a data preprocessing step, aiming to eliminate the non-robust features and preserve the ro

2024

Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks

EMNLP 2024main

Adversarial textual examples reveal the vulnerability of natural language processing (NLP) models. Most existing text attack methods are designed for English text, while the robust implementation of the second popular language, i.e., Chinese with 1 billion users, is greatly underestimated. Although…