Scholar
Jiayang Liu
Google Scholar ID: 4DTnkkkAAAAJ
University of Science and Technology of China
Adversarial example
AI security
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
468
H-index
9
i10-index
8
Publications
16
Co-authors
10
list available
Publications
14 items
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
2026
Cited
0
Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance
2026
Cited
0
Near-Duplicate Families Break Exact-Record Membership Inference
2026
Cited
0
TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks
2026
Cited
0
Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models
2026
Cited
0
The Benchmark Illusion: Pruned LLMs Can Pass Multiple Choice but Fail to Answer
2026
Cited
0
SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition
2026
Cited
0
RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System
2025
Cited
0
Load more
Co-authors
8 total
weiming zhang
University of Science and Technology of China
Nenghai Yu
University of Science and Technology of China
Kejiang Chen
Department of Electronic Engineering and Information Science, University of Science and Technology
Jun Sakuma
Institute of Science Tokyo (Tokyo Institute of Technology), School of Computing
Xiaoyi Dong
Microsoft GenAI
Zehua Ma
University of Science and Technology of China
Zhou Wenbo
University of Science and Technology of China
Jie Zhang (张杰)
Research Scientist, CFAR, A*STAR | NTU | USTC
