Scholar

Zenghui Yuan

Google Scholar ID: YhrXMbkAAAAJ

Huazhong University of Science and Technology

AI SecurityBackdoor

Google Scholar↗

Citations & Impact

All-time

Citations

324

H-index

7

i10-index

7

Publications

11

Co-authors

0

Contact

No contact links provided.

Publications

7 items

An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs

2025

Cited

0

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

2025

Cited

0

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

2025

Cited

0

Prompt Injection Attack to Tool Selection in LLM Agents

2025

Cited

0

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

2025

Cited

0

Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation

2025

Cited

0

Optimization-based Prompt Injection Attack to LLM-as-a-Judge

Conference on Computer and Communications Security · 2024

Cited

23

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)