Hongwei Li

Venues

Frequent coauthors

Papers

1. ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
   AAAI 2026 ·

   Zihan Wang

   DBLP profile ↗ORCID search ↗
2. MPMA: Preference Manipulation Attack Against Model Context Protocol
   AAAI 2026 ·

   Zihan Wang

   DBLP profile ↗ORCID search ↗
3. MartDE: A Privacy-Preserving and Cost-Efficient Evaluation Framework for Data Marketplaces
   AAAI 2026 ·

   Xinyuan Qian

   DBLP profile ↗ORCID search ↗
4. The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
   ACL 2026 ·

   Rui Zhang

   DBLP profile ↗ORCID search ↗
5. Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
   ICML 2025 ·

   Shuai Yuan

   DBLP profile ↗ORCID search ↗
6. The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
   NeurIPS 2025 ·

   Shuai Yuan

   DBLP profile ↗ORCID search ↗
7. The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
   ICML 2025 ·

   Rui Zhang

   DBLP profile ↗ORCID search ↗
8. Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
   AAAI 2025 ·

   Jiaming He

   DBLP profile ↗ORCID search ↗