Profiles2023-2026
Zenghui Yuan
Huazhong University of Science and Technology
5Papers
0Last author
6Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers5
- Prompt Injection Attack to Tool Selection in LLM AgentsAuthor 2 of 6NDSS 2026 · 181 citations
- Merge Hijacking: Backdoor Attacks to Model Merging of Large Language ModelsAuthor 1 of 5ACL 2025 · 5 citations
- BadToken: Token-level Backdoor Attacks to Multi-modal Large Language ModelsAuthor 1 of 5CVPR 2025
- Optimization-based Prompt Injection Attack to LLM-as-a-JudgeAuthor 2 of 7CCS 2024 · 33 citations
- You Are Catching My Attention: Are Vision Transformers Bad Learners under Backdoor Attacks?Author 1 of 4CVPR 2023
