Gongxi Zhu
4 papers · 2024–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
federated learning
(3)
privacy attack
(1)
synthetic data generation
(1)
optimal control
(1)
privacy preserving
(1)
foundation model
(1)
gradient norm
(1)
privacy-utility trade-off
(1)
right to be forgotten
(1)
non-iid data
(1)
client-server architecture
(1)
privacy risk
(1)
membership inference
(1)
likelihood ratio test
(1)
membership inference attack
(1)
bi-objective optimization
(1)
group relative policy optimization
(1)
reconstruction attack
(1)
communication round
(1)
federated machine unlearning
(1)
Papers
FedGRPO: Privately Optimizing Foundation Models with Group-Relative Rewards from Domain Clients
AAAI 2026
PrivSynth: Alternating and Control-Based Optimization for Privacy and Utility in Synthetic Data
CVPR 2026
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
CVPR 2025
Unlearning during Learning: An Efficient Federated Machine Unlearning Method
IJCAI 2024