Wenjie Zhu
Wenjie Zhu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Donghong Sun
Tsinghua University, Beijing, China
1 shared publication - Haixin Duan
Tsinghua University, Beijing, China
1 shared publication - Jiawei Zhou
QI-ANXIN Technology Research Institute, Beijing, China
1 shared publication - Lingyun Ying
QI-ANXIN Technology Research Institute, Beijing, China
1 shared publication - Xiaoxue Huang
QI-ANXIN Technology Research Institute, Beijing, China
1 shared publication - Yacong Gu
Tsinghua University; Tsinghua University-QI-ANXIN Group JCN, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4582-4596
Your Space is My Zone: Demystifying the Security Risks of AI-Powered Applications on Pre-Trained Model Hubs
AI-powered Applications (AI-Apps) on platforms such as Hugging Face give anyone online access to pre-trained models. They lower the barrier to adoption, but they also open an unexplored attack surface: AI-Apps are written by untrusted parties, isolated weakly, and frequently misconfigured. We present the first systematic security analysis of AI-Apps across three leading platforms. Mapping the AI-App lifecycle onto established risk taxonomies (e.g., OWASP) yields five threat categories and ten attack vectors, ranging from generic web flaws to platform-level design faults. Our analysis exposes broken access control, insecure resource reuse, insufficient input validation, and sensitive data exposure. Two vectors are architecture-induced: they survive best-practice development because their root cause lies in the platform rather than in any application. We also show how familiar issues, such as world-readable logs, are amplified in this ecosystem. To assess real-world impact, we built the analysis framework Insightor and ran it over more than 970,000 public AI-Apps. From its output we manually confirmed AI-Apps that leak developer credentials through world-readable logs, AI-Apps whose input handling permits arbitrary code execution, and 27 AI-Apps carrying deliberately planted malicious code. We responsibly disclosed all findings to the affected platforms and developers.
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4582-4596
Open AccessYour Space is My Zone: Demystifying the Security Risks of AI-Powered Applications on Pre-Trained Model Hubs
AI-powered Applications (AI-Apps) on platforms such as Hugging Face give anyone online access to pre-trained models. They lower the barrier to adoption, but they also open an unexplored attack surface: AI-Apps are written by untrusted parties, isolated weakly, and frequently misconfigured. We present the first systematic security analysis of AI-Apps across three leading platforms. Mapping the AI-App lifecycle onto established risk taxonomies (e.g., OWASP) yields five threat categories and ten attack vectors, ranging from generic web flaws to platform-level design faults. Our analysis exposes broken access control, insecure resource reuse, insufficient input validation, and sensitive data exposure. Two vectors are architecture-induced: they survive best-practice development because their root cause lies in the platform rather than in any application. We also show how familiar issues, such as world-readable logs, are amplified in this ecosystem. To assess real-world impact, we built the analysis framework Insightor and ran it over more than 970,000 public AI-Apps. From its output we manually confirmed AI-Apps that leak developer credentials through world-readable logs, AI-Apps whose input handling permits arbitrary code execution, and 27 AI-Apps carrying deliberately planted malicious code. We responsibly disclosed all findings to the affected platforms and developers.