Zehang Deng

PhD student, Swinburne University of Technology

Joined

April 2024

Names

Zehang Deng (Preferred)

Emails

****@swin.edu.au (Confirmed)

Personal Links

Career & Education History

PhD student

Swinburne University of Technology (swin.edu.au)

2023 – 2027

MS student

Monash University (monash.edu)

2022 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Sheng Wen

2023 – Present

Expertise

Model Inversion Attack

2023 – 2024

AI Security

2022 – 2024

LLM Security

2022 – 2024

Publications

Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
Haocheng Luo, Zehang Deng, Thanh-Toan Do, Mehrtash Harandi, Dinh Phung, Trung Le
- ICLR 2026 Poster
- Readers: Everyone
Adaptive Gray: Reducing Color Dependency to Improve Generalization in Deepfake Detection
Xi Tang, Wanlun Ma, Zehang Deng, Derui Wang, Jason Xue, Sheng Wen, Yang Xiang
- Submitted to ICLR 2026
- Readers: Everyone
Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-Enabled Critical Infrastructure
Zehang Deng, Ruoxi Sun, Minhui Xue, Sheng Wen, Seyit Camtepe, Surya Nepal, Yang Xiang
- IEEE Trans. Dependable Secur. Comput. 2025
- Readers: Everyone
Systematic Analysis of MCP Security
Yongjian Guo, Puzhuo Liu, Wanlun Ma, Zehang Deng, Xiaogang Zhu, Peng Di, Xi Xiao, Sheng Wen
- CoRR 2025
- Readers: Everyone
AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways
Zehang Deng, Yongjian Guo, Changzhou Han, Wanlun Ma, Junwu Xiong, Sheng Wen, Yang Xiang
- ACM Comput. Surv. 2025
- Readers: Everyone
Exploring DeepSeek: A Survey on Advances, Applications, Challenges and Future Directions
Zehang Deng, Wanlun Ma, Qing-Long Han, Wei Zhou, Xiaogang Zhu, Sheng Wen, Yang Xiang
- IEEE CAA J. Autom. Sinica 2025
- Readers: Everyone
Hardening LLM Fine-Tuning: From Differentially Private Data Selection to Trustworthy Model Quantization
Zehang Deng, Ruoxi Sun, Jason Xue, Wanlun Ma, Sheng Wen, Surya Nepal, Yang Xiang
- IEEE Trans. Inf. Forensics Secur. 2025
- Readers: Everyone
Codebreaker: Dynamic Extraction Attacks on Code Language Models
Changzhou Han, Zehang Deng, Wanlun Ma, Xiaogang Zhu, Minhui Xue, Tianqing Zhu, Sheng Wen, Yang Xiang
- SP 2025
- Readers: Everyone
GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-Resolution
Yuzhen Li, Zehang Deng, Yuxin Cao, Lihua Liu
- MM2024 Poster
- Readers: Everyone

Co-Authors

View all 28 co-authors