Xiangfang Li

Identifiers

No identifiers captured yet.

Papers (1)

1. Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks cs.CR · 2025 · author #5

Mentions

No mention provenance yet.

Frequent Coauthors

• Bo Li 1 shared papers
• Haihui Fan 1 shared papers
• Haotian Jin 1 shared papers
• Lin Shen 1 shared papers
• Yang Li 1 shared papers