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 TSE. 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

High Efficient SQL generation from Natural Language Description Agentic AI for Data Generation in Low-Resource Software Engineering Tasks Agents for Trustworthy Code Generation Automated Scenario Test Case Generation for Autonomous Driving Systems

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

 

 

Publications

• Zhu, D., Chen, D., Grossklags, J., Ma, L., Fritz, M., Schimmler, S. IPAuditor: Privacy Violation in Data Release Using Diffusion-based Generative Models. IEEE Transactions on Dependable and Secure Computing 2026.
• Chen, Z., Zhu, D., Yao, K., Shang, W., Chen, J., Geng, J., Pretschner, A., Grossklags, J., Hauswirth, M., Schimmler, S. LLM4JMH: Studying the Use of LLMs for Generating Java Performance Microbenchmarks. ICSE 2026.
• Zhu, D., Bergemann, S., Sadeghi, M., Atkinson, C., Pretschner, A. Data Protection Vulnerabilities Assessment for Cross-Organizational Consistency Checking in TEE. MSSiS@ICSE 2026.
• Zhu, D., Chen, D., Chen, J., Grossklags, J., Pretschner, A., Shang, W. More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation. NeurIPS 2025.
• Bergemann, S., Bayha, A., Zhu, D., Sadeghi, M., Atkinson, C., Pretschner, A. Mind the Leak: Formalizing Confidentiality Preservation Assessment of Multi-Model Consistency Checking Systems. SAM 2025.
• Li, Q., Geng, J., Chen, Z., Zhu, D., Wang, Y., Ma, C., Lyu, C., Karray, F. HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs. ACL 2025.
• Li, Q., Geng, J., Zhu, D., Chen, Z., Song, K., Ma, L., Karray, F. Internal Activation Revision: Safeguarding Vision Language Models without Parameter Update. AAAI 2025.
• Zhu, D., Chen, D., Wu, X., Geng, J., Li, Z., Grossklags, J., Ma, L. PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques. NeurIPS 2024 (Spotlights).
• Zhu, D., Chen, D., Li, Q., Chen, Z., Ma, L., Grossklags, J., Fritz, M. PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics. Findings of NAACL 2024.
• Zhu, D., Chen, J., Zhou, X., Shang, W., Hassan, A. E., Grossklags, J. Vulnerabilities of Data Protection in Vertical Federated Learning Training: A Comprehensive Analysis. IEEE Transactions on Information Forensics and Security 2024.
• Sun, Y., Duan, L., Mendes, R., Zhu, D., Xia, Y., Li, Y., Fischer, A. Exploiting Internal Randomness for Privacy in Vertical Federated Learning. ESORICS 2024.
• Song, D., Xie, X., Song, J., Zhu, D., Huang, Y., Juefei-Xu, F., Ma, L. LUNA: A Model-Based Universal Analysis Framework for Large Language Models. IEEE Transactions on Software Engineering 2024.
• Chen, Z., Geng, J., Zhu, D., Li, Q., Schimmler, S., Hauswirth, M. Towards Trustworthy Dataset Distillation: A Benchmark of Privacy, Fairness and Robustness. IJCNN 2024.
• Li, Q., Geng, J., Lyu, C., Zhu, D., Panov, M., Karray, F. Reference-free Hallucination Detection for Large Vision-Language Models. Findings of EMNLP 2024.
• Li, Z., Zhu, D., Hu, Y., Xie, X., Ma, L., Zheng, Y., Song, Y., Chen, Y., Zhao, J. Neural Episodic Control with State Abstraction. ICLR 2023 (Spotlights).
• Li, Z., Wu, X., Zhu, D., Cheng, M., Chen, S., Zhang, F., Xie, X., Ma, L., Zhao, J. Generative Model-Based Testing on Decision-Making Policies. ASE 2023.
• Eslami Abyane, A., Zhu, D., de Souza, R. M., Ma, L., Hemmati, H. 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)
• Zhu, D., Chen, J., Shang, W., Zhou, X., Grossklags, J., Hassan, A. E. DeepMemory: Model-based Memorization Analysis of Deep Neural Language Models. ASE 2021.
• Wang, W., Zhu, D., Alkhouli, T., Gan, Z., Ney, H. Neural Hidden Markov Model for Machine Translation. ACL 2018 (Oral).
• Wang, W., Alkhouli, T., Zhu, D., Ney, H. Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation. ACL 2017.