Zhaoxi Zhang

Orcid: 0000-0002-3813-2776

Affiliations:
  • University of Technology Sydney, School of Computer Science, Sydney, Australia
  • Deakin University, School of Information Technology, Geelong, Australia
  • Southwest University, School of Computer and Information Science, Chongqing, China


According to our database1, Zhaoxi Zhang authored at least 11 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Less Is More - Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models.
CoRR, January, 2026

Character-Level Perturbations Disrupt LLM Watermarks.
Proceedings of the 33rd Annual Network and Distributed System Security Symposium, 2026

2025
Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks.
CoRR, April, 2025

Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning.
Proceedings of the IEEE Symposium on Security and Privacy, 2025

When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning.
Proceedings of the 20th ACM Asia Conference on Computer and Communications Security, 2025

2024
Large Language Model Watermark Stealing With Mixed Integer Programming.
CoRR, 2024

Stealing Watermarks of Large Language Models via Mixed Integer Programming.
Proceedings of the Annual Computer Security Applications Conference, 2024

2023
Masked Language Model Based Textual Adversarial Example Detection.
Proceedings of the 2023 ACM Asia Conference on Computer and Communications Security, 2023

2022
Evaluating Membership Inference Through Adversarial Robustness.
Comput. J., 2022

Self-Supervised Adversarial Example Detection by Disentangled Representation.
Proceedings of the IEEE International Conference on Trust, 2022

2021
Self-Supervised Adversarial Example Detection by Disentangled Representation.
CoRR, 2021


  Loading...