Zichen Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zichen Xie has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Chenyuan Yang
University of Illinois at Urbana-Champaign, Champaign, USA
1 shared publication - Haoyu Li
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Kangjie Lu
University of Minnesota, Minneapolis, Minnesota, USA
1 shared publication - Lingming Zhang
University of Illinois at Urbana-Champaign, Champaign, USA
1 shared publication - Peiyu Liu
Zhejiang University, Hangzhou, China
1 shared publication - Shouling Ji
Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 655-669
KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 655-669
Open AccessKNighter: Transforming Static Analysis with LLM-Synthesized Checkers
- Open Access
- 22 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (ISSTA) , 113-136
Beyond Static Pattern Matching? Rethinking Automatic Cryptographic API Misuse Detection in the Era of LLMs
While the automated detection of cryptographic API misuses has progressed significantly, its precision diminishes for intricate targets due to the reliance on manually defined patterns. Large Language Models (LLMs) offer a promising context-aware understanding to address this shortcoming, yet the stochastic nature and the hallucination issue pose challenges to their applications in precise security analysis. This paper presents the first systematic study to explore LLMs’ application in cryptographic API misuse detection. Our findings are noteworthy: The instability of directly applying LLMs results in over half of the initial reports being false positives. Despite this, the reliability of LLM-based detection could be significantly enhanced by aligning detection scopes with realistic scenarios and employing a novel code & analysis validation technique, achieving a nearly 90% detection recall. This improvement substantially surpasses traditional methods and leads to the discovery of previously unknown vulnerabilities in established benchmarks. Nevertheless, we identify recurring failure patterns that illustrate current LLMs’ blind spots, including cryptographic knowledge deficiencies and code semantics misinterpretations. Leveraging these findings, we deploy an LLM-based detection system and uncover 63 new vulnerabilities (47 confirmed, 7 already fixed) in open-source Java and Python repositories, including prominent projects like Apache.
- 22 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (ISSTA) , 113-136
Open AccessBeyond Static Pattern Matching? Rethinking Automatic Cryptographic API Misuse Detection in the Era of LLMs
While the automated detection of cryptographic API misuses has progressed significantly, its precision diminishes for intricate targets due to the reliance on manually defined patterns. Large Language Models (LLMs) offer a promising context-aware understanding to address this shortcoming, yet the stochastic nature and the hallucination issue pose challenges to their applications in precise security analysis. This paper presents the first systematic study to explore LLMs’ application in cryptographic API misuse detection. Our findings are noteworthy: The instability of directly applying LLMs results in over half of the initial reports being false positives. Despite this, the reliability of LLM-based detection could be significantly enhanced by aligning detection scopes with realistic scenarios and employing a novel code & analysis validation technique, achieving a nearly 90% detection recall. This improvement substantially surpasses traditional methods and leads to the discovery of previously unknown vulnerabilities in established benchmarks. Nevertheless, we identify recurring failure patterns that illustrate current LLMs’ blind spots, including cryptographic knowledge deficiencies and code semantics misinterpretations. Leveraging these findings, we deploy an LLM-based detection system and uncover 63 new vulnerabilities (47 confirmed, 7 already fixed) in open-source Java and Python repositories, including prominent projects like Apache.