Scholar
Zheng Li
Google Scholar ID: xEAaaGsAAAAJ
Professor, Shandong University
Citations & Impact
Citations
1,504
H-index
16
i10-index
17
Publications
20
Co-authors
24
list available
Publications
Resume (English only)
Academic Achievements
- - 2025 IEEE S&P paper “Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models”
- - 2025 USENIX Security paper “Membership Inference Attacks Against Vision-Language Models”
- - 2025 USENIX Security paper “Enhanced Label-Only Membership Inference Attacks with Fewer Queries”
- - 2024 Best Paper Finalist at CSAW Europe paper “DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models”
- - 2024 EMNLP paper “ModScan: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities”
- - 2024 ERCIM WG STM Best Ph.D. Thesis Award
- - 2024 CCS paper “Membership Inference Attacks Against In-Context Learning”
- - 2025 PETS paper “A Comprehensive Study of Privacy Risks in Curriculum Learning”
- - 2024 CCS paper “BadMerging: Backdoor Attacks Against Model Merging”
- - 2024 CCS paper “SeqMIA: Sequential-Metric Based Membership Inference Attack”
- - 2024 ECAI paper “Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders”
- - 2024 ICASSP paper “Detection and Attribution of Models Trained on Generated Data”
Research Experience
- - [2025.01 – current] Professor at School of Cyber Science and Technology, Shandong University
- - [2023.11 – 2024.12] Postdoc at CISPA Helmholtz Center for Information Security, supervised by Dr. Yang Zhang
- - [2022.07 – 2022.10] Research Intern at Bell Lab
Education
- - 2013.09 – 2017.06: Bachelor in Computer Science, Shandong University, supervised by Prof. Shanqing Guo
- - 2017.09 – 2020.06: Master in Computer Science, Shandong University, supervised by Prof. Shanqing Guo
- - 2021.02 – 2023.10: Ph.D. in Computer Science, CISPA Helmholtz Center for Information Security, supervised by Dr. Yang Zhang
Background
- Research Interests: Trustworthy Machine Learning (Privacy, Security, and Safety), especially analyzing machine learning model vulnerabilities, including privacy attacks (MIA and AIA), backdoors, and data poison attacks. Additionally, working on technical solutions against unethical AI systems.
Miscellany
- Looking for motivated PhD/master students (25 Fall) and research assistants to join his group.
