CV - Xun Wang

Download CV (PDF)

Contact: xun.wang@cispa.de · xun.wang@tum.de

Research: Trustworthy and efficient machine learning: privacy-preserving model adaptation and post-training (differential privacy, privacy auditing); model provenance and ownership (fingerprinting, IP protection); and trustworthy world models.

Education

• Ph.D. in Computer Science, Technical University of Munich & CISPA, Nov 2023–present (expected 2027)
  • Advisor: Michael Backes
• M.Sc. in Robotics, Cognition, Intelligence, Technical University of Munich, Oct 2020–Aug 2023
  • Graduated with High Distinction
  • Thesis: Architecture-Agnostic Neural Network Pruning
• B.Eng. in Vehicle Engineering, Tongji University, Sep 2015–Jul 2020

Publications

• Auditing Privacy Leakage in Tabular Foundation Model Embeddings

  Xun Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch
  NeurIPS 2026

• AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes

  Xun Wang, Bihe Zhao, Michael Backes, Franziska Boenisch, Adam Dziedzic
  EMNLP 2026

• Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

  Bartłomiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, Adam Dziedzic
  ICLR 2026 (Oral)

• Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs

  Xun Wang, Jing Xu, Franziska Boenisch, Michael Backes, Christopher A. Choquette-Choo, Adam Dziedzic
  ICML 2025

• Provenance Tracing for World Models: Was this Agent Trained in my World Model?

  Bihe Zhao, Xun Wang, Franziska Boenisch, Adam Dziedzic
  Under review (2026)

• Frequency-Domain Model Fingerprinting for Image Autoregressive Models

  Xun Wang*, Vincent Hanke*, Jing Xu, Michael Backes, Franziska Boenisch, Adam Dziedzic (*Equal contribution)
  AIGOV@AAAI 2026 (Oral)

• Structurally Prune Anything: Any Architecture, Any Framework, Any Time

  Xun Wang, John Rachwan, Stephan Günnemann, Bertrand Charpentier
  arXiv preprint (2024)

Research experience

• Doctoral Researcher, TUM & CISPA, Nov 2023–present. Saarbrücken, Germany.
• Student Research Assistant, Technical University of Munich, Aug 2021–Mar 2022. Chair of Informatics 6, Munich, Germany.

Honors & awards

• Oral Presentation, ICLR (top ~1.8% of submissions), 2026
• Oral Presentation, AIGOV@AAAI, 2026
• Gold Reviewer Award, ICLR, 2025
• Graduated with High Distinction, M.Sc., TUM, 2023

Teaching, service & skills

• Co-organizer, First CISPA European Cybersecurity and AI Hackathon
• Teaching Assistant, Machine Learning, TUM, Munich, Oct 2021–Mar 2022
• AI-assisted development: Proficient with Codex and Claude Code
• ML / Deep Learning: PyTorch, Hugging Face Transformers, distributed training, Slurm
• Languages: Chinese (native), English (fluent), German (B2)