Scholar
Yixiang Qiu
Google Scholar ID: kxotrxgAAAAJ
Tsinghua Shenzhen International Graduate School
Citations & Impact
Citations
101
H-index
4
i10-index
3
Publications
10
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - 'Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors', EMNLP 2025
- - 'ICAS: Detecting Training Data from Autoregressive Image Generative Models', ACM MM 2025
- - 'Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks', ICLR 2025
- - 'A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks', ECCV 2024
- Reviewer for: WCSP 2024, ICLR 2025
- Awards:
- - First class scholarship × 2, Second class scholarship × 1, Harbin Institute of Technology, Shenzhen, 2023.09
- - Fang Binxing Academician Scholarship, Harbin Institute of Technology, Shenzhen, 2023.03
- - Chinese National Scholarship for Undergraduate Students (Top 1.5%), Harbin Institute of Technology, Shenzhen, 2022.12
- - Provincial First Prize in the China Undergraduate Mathematical Contest in Modeling (CUMCM), 2022.09
- - National Third Prize in the National Student Computer System Capability Challenge (NSCSCC), 2022.08
- - Provincial First Prize in the Chinese Mathematics Competitions (CMC), 2021.12
Research Experience
- Conducting research in the ITML lab, focusing on the security of multi-modal large language models.
Education
- Received B.S. in Computer Science and Technology from Harbin Institute of Technology, Shenzhen in 2024; currently a second-year master's student in the ITML lab at Tsinghua Shenzhen International Graduate School, supervised by Prof. Bin Chen and Prof. Shu-Tao Xia.
Background
- Research interests include Trustworthy AI, Generative Models, Computer Vision, and Deep Learning. Currently, working on the security for multi-modal large language models.
