CV

Publications

• Zirui Gong, et al. “Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning”, in IEEE Symposium on Security and Privacy 2025 (S&P).
• Zirui Gong, et al. “Agramplifier: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification”, IEEE Transactions on Information Forensics and Security (TIFS), vol. 19, 2023, pp. 1241–1250.
• Li, Yuqi*, Zirui Gong*, et al. “Production Evaluation of Citrus Fruits Based on the YOLOv5 Compressed by Knowledge Distillation”, in International Conference on Computer Supported Cooperative Work in Design (CSCWD).

Research Interests

• Federated Learning Security
• Privacy-Preserving Machine Learning
• Adversarial Attacks & Defenses
• Secure Distributed Systems

Research Experience

PhD Researcher

Griffith University, Gold Coast, QLD
Feb 2024 – Present

• Investigated methods to improve security and privacy in Federated Learning, ensuring safer distributed machine learning.

Research Assistant

Deakin University, Melbourne, VIC
Mar 2023 – Oct 2023

• Focused on object detection in decentralized structures to enhance real-world detection performance in the meat industry.

Honours Researcher

Deakin University, Melbourne, VIC
Jun 2022 – Jun 2023

• Explored strategies to improve the robustness of Federated Learning systems against Byzantine threats and failures.

Academic Activities

I actively contribute to the academic community by:

• Assistant in reviewing papers for top AI and security conferences (e.g., ICLR, CVPR, IJCAI, AAAI, AISTATS, AsiaCCS).
• Presenting ongoing research within the TrustAGI Lab.
• Mentoring postgraduate students on backdoor and fine-grained poisoning attacks in FL.

Awards & Scholarships

• GU International Postgraduate Research Scholarship, 2024–2027
• GU Postgraduate Research Scholarship, 2024–2027
• STEM Scholarship of Deakin University, 2022 and 2023
• Third Class Scholarship of Southwest University, 2019 and 2020
• Internet Excellence Award, Chongqing Municipal Level of National College Student Innovation and Entrepreneurship Competition, 2020

Mentorship Experience

• Guide and collaborate with a postgraduate student on launching fine-grained attacks in ranking-based Federated Learning, with the work submitted to IJICIA.
• Supervise and mentor graduate students on backdoor attacks in the Federated Learning domain.

Teaching

At Griffith, I work as a Teaching Assistant, contributing to the following courses:

• Trustworthy AI – covering adversarial machine learning, explainability, and fairness.
• Ethical Hacking – assisting with penetration testing, secure coding, and risk analysis.
• Programming Principles (Python) – guiding students in algorithm design and debugging.