Xun Wang

Xun Wang

Ph.D student at CISPA

Publications - Xun Wang

You can also find my articles on my Google Scholar profile.

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

Bartłomiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch

A systematic benchmark investigating privacy risks under differentially private adaptations of LLMs using state-of-the-art attacks such as robust membership inference and canary data extraction.

ICLR 2026 (Oral) ,

Download Paper

Frequency-Domain Model Fingerprinting for Image Autoregressive Models

Xun Wang*, Vincent Hanke*, Jing Xu, Michael Backes, Franziska Boenisch, Adam Dziedzic (*Equal contribution)

FreqIAR: A frequency-domain approach for fingerprinting image autoregressive models.

AIGOV Workshop @ AAAI 2026 (Oral) ,

Download Paper

Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs

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

A novel framework for transferring soft prompts between LLMs while preserving privacy through differential privacy and knowledge distillation techniques.

ICML 2025 ,

Download Paper | Project Page

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

Xun Wang, John Rachwan, Stephan Günnemann, Bertrand Charpentier

A versatile structured pruning framework that works across any neural network architecture, framework, and training stage, introducing OBSPA for post-training pruning without fine-tuning.

arXiv preprint ,

Download Paper | Project Page