Bao-di Liu

According to our database, Bao-di Liu authored at least 2 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance.

Ao Wang, Xinghao Yang, Yongshun Gong, Wei Liu, Bao-di Liu, Weifeng Liu

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

Disentangled Information Bottleneck for Adversarial Text Defense.

Yidan Xu, Xinghao Yang, Wei Liu, Bao-di Liu, Weifeng Liu

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025