Skip to content
CyberPUNK Lab

Selected publications in cybersecurity, privacy, dependable systems, and trustworthy AI.

2026

SlaClip: Gradient Norm Slacks can be Indicator for Adaptive Clipping in DP-SGD

Shuyan Zou, Shaowei Wang, Zhanxing Zhu, Jin Li, Changyu Dong, Vladimiro Sassone, Han Wu

ICML 2026 Spotlight (top 2.2%)
Representative figure for SlaClip: Gradient Norm Slacks can be Indicator for Adaptive Clipping in DP-SGD
PDF Project

An Adaptive Mini-Batching Strategy for Reliable Streaming Data Delivery in Real-Time

Han Wu, Zhihao Shang, Huaming Wu, Katinka Wolter

IEEE Transactions on Reliability
Representative figure for An Adaptive Mini-Batching Strategy for Reliable Streaming Data Delivery in Real-Time
DOI

Peeling the Layers of Privacy-Utility Onion on Tabular Data

Jiawei Wang, Zilong Zhao, Leonardo Aniello, Han Wu

EuroMLSys Workshop 2026
Representative figure for Peeling the Layers of Privacy-Utility Onion on Tabular Data
DOI

2025

Beyond Statistical Estimation: Differentially Private Individual Computation via Shuffling

Shaowei Wang, Changyu Dong, Xiangfu Song, Jin Li, Zhili Zhou, Di Wang, Han Wu

USENIX Security 2025 Honorable Mention
Representative figure for Beyond Statistical Estimation: Differentially Private Individual Computation via Shuffling
PDF

GTV: Generating Tabular Data via Vertical Federated Learning

Zilong Zhao, Han Wu, Aad van Moorsel, Lydia Y. Chen

DSN 2025
Representative figure for GTV: Generating Tabular Data via Vertical Federated Learning
PDF

Impacts of Physical-Layer Information on Epidemic Spreading in Cyber-Physical Networked Systems

Xianglai Yuan, Yichao Yao, Han Wu, Minyu Feng

IEEE TCSI 2025
Representative figure for Impacts of Physical-Layer Information on Epidemic Spreading in Cyber-Physical Networked Systems
DOI