


default search action
"Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP ..."
Haotian Jin et al. (2026)
- Haotian Jin

, Yang Li, Haihui Fan, Lin Shen, Xiangfang Li, Bo Li:
Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks. AAAI 2026: 37472-37480

manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.


Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCID













