About me

Derui Zhu is a researcher at the Technical University of Munich. His research lies at the intersection of software engineering, natural language processing, security, and privacy, focusing on providing quality assurance to support the design and deployment of trustworthy AI systems in practice. His research has been published in leading software engineering, AI, and security venues, such as ICSE, ASE, NeurIPS, TIFS, and ASE. Prior to his academic career, he spent some years working at JD.COM and Orange Business, where he addressed practical business challenges related to AI and software systems.

Thesis Topics

If you are interested in thesis supervision, please do not hesitate to contact me. Be sure to include your current CV and transcripts, as well as a short motivation letter stating when you would like to start your thesis. You are also welcome to suggest your own topic.

Open Topics

Improved SQL generation from text2sql Agentic AI for data generation for low-resource software engineering tasks Agent for trustworthy code generation Scenario test case generation for autonomous driving systems

-  Master's Thesis -  Master's Thesis -  Master's Thesis -  Master's Thesis

 

 

Publications

• Zongxiong Chen, Derui Zhu*, Kundi Yao, Weiyi Shang, Jinfu Chen, Jiahui Geng, Alexander Pretschner, Jens Grossklags, Manfred Hauswirth, Sonja Schimmler. LLM4JMH: Studying the Use of LLMs for Generating Java Performance Microbenchmarks. ICSE 2026 (Research Track).
• Derui Zhu, Dingfan Chen, Jinfu Chen, Jens Grossklags, Walter Pretschner, Weiyi Shang. More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation. NeurIPS 2025.
• Qing Li, Jiahui Geng, Zongxiong Chen, Derui Zhu, Yuxia Wang, Congbo Ma, Chenyang Lyu, Fakhri Karray. HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs. ACL 2025 (Oral).
• Qing Li, Jiahui Geng, Derui Zhu, Zongxiong Chen, Kun Song, Lei Ma, Fakhri Karray. Internal Activation Revision: Safeguarding Vision Language Models without Parameter Update. AAAI 2025 (Oral).
• Derui Zhu, Dingfan Chen, Xiongfei Wu, Jiahui Geng, Zhuo Li, Jens Grossklags, Lei Ma. PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques. NeurIPS 2024 (Spotlights).
• Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz. PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics. Findings of NAACL 2024.
• Derui Zhu, Jinfu Chen, Xuebing Zhou, Weiyi Shang, Ahmed E. Hassan, Jens Grossklags. Vulnerabilities of Data Protection in Vertical Federated Learning Training: A Comprehensive Analysis. IEEE TIFS 2024.
• Yulian Sun, Li Duan, Ricardo Mendes, Derui Zhu, Yue Xia, Yong Li, Asja Fischer. Exploiting Internal Randomness for Privacy in Vertical Federated Learning. ESORICS 2024.
• Da Song, Xuan Xie, Jiayang Song, Derui Zhu, Yuheng Huang, Felix Juefei-Xu, Lei Ma. LUNA: A Model-Based Universal Analysis Framework for Large Language Models. IEEE TSE 2024.
• Zongxiong Chen, Jiahui Geng, Derui Zhu, Qing Li, Sonja Schimmler, Manfred Hauswirth. Towards Trustworthy Dataset Distillation: A Benchmark of Privacy, Fairness and Robustness. IJCNN 2024.
• Qing Li, Jiahui Geng, Chenyang Lyu, Derui Zhu, Maxim Panov, Fakhri Karray. Reference-free Hallucination Detection for Large Vision-Language Models. Findings of EMNLP 2024.
• Zhuo Li, Derui Zhu, Yujing Hu, Xiaofei Xie, Lei Ma, Yan Zheng, Yan Song, Yingfeng Chen, Jianjun Zhao. Neural Episodic Control with State Abstraction. ICLR 2023 (Spotlights).
• Zhuo Li, Xiongfei Wu, Derui Zhu, Mingfei Cheng, Siyuan Chen, Fuyuan Zhang, Xiaofei Xie, Lei Ma, Jianjun Zhao. Generative Model-Based Testing on Decision-Making Policies. ASE 2023.
• Amin Eslami Abyane, Derui Zhu, Roberto Medeiros de Souza, Lei Ma, Hadi Hemmati. Towards Understanding Quality Challenges of the Federated Learning: A First Look from the Lens of Robustness. Empirical Software Engineering 2023. (Invited ICSE 2023 Journal First)
• Derui Zhu, Jinfu Chen, Weiyi Shang, Xuebing Zhou, Jens Grossklags, Ahmed E. Hassan. DeepMemory: Model-based Memorization Analysis of Deep Neural Language Models. ASE 2021.
• Weiyue Wang, Derui Zhu, Tamer Alkhouli, Zixuan Gan, Hermann Ney. Neural Hidden Markov Model for Machine Translation. ACL 2018 (Oral).
• Weiyue Wang, Tamer Alkhouli, Derui Zhu, Hermann Ney. Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation. ACL 2017.