Zirui Gong
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Crypto×1
Frequent co-authors
Research Timeline
2026
ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
The paper introduces ARES, a novel and practical gradient inversion attack that reconstructs sensitive training samples from large batch updates in Federated Learning without requiring architectural modifications.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CRRecentMar 18, 2026
ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
Zirui Gong, Leo Yu Zhang, Yanjun Zhang, Viet Vo +3 more
The paper introduces ARES, a novel and practical gradient inversion attack that reconstructs sensitive training samples from large batch updates in Federated Learning without requiring architectural m…
View →