Practical Differentially Private and Byzantine-resilient Federated Learning

Summary: Practical DP-SGD with Byzantine-resilient aggregation for FL; analyzes DP-Byzantine interaction. Leverages DP noise to enhance aggregation; validates theory and experiments, achieving high accuracy under strong DP and up to 90% Byzantine. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6684
Venue: SIGMOD
Year: 2023
Pagerank: 5.8983442e-05
Overall Rank: 6,366 | 56.33%
DOI: 10.1145/3589264

Incoming Non-self Citations Over Time

Authors

1. Zihang Xiang (King Abdullah University of Science and Technology)
2. Tianhao Wang (University of Virginia)
3. Wanyu Lin (Hong Kong Polytechnic University)
4. Di Wang (King Abdullah University of Science and Technology)

BibTeX Citation

@inproceedings{xiang_sigmod23,
        title = {{Practical Differentially Private and Byzantine-resilient Federated Learning}},
        author = {Xiang, Zihang and Wang, Tianhao and Lin, Wanyu and Wang, Di},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3589264},
        url = {https://dl.acm.org/doi/10.1145/3589264},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,456	Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs	2024	VLDB	5.4217837e-05
10,934	PS-MI: Accurate, Efficient, and Private Data Valuation in Vertical Federated Learning	2025	VLDB	5.093636e-05
11,191	A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition	2024	SIGMOD	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 4 of 4 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
1,959	VF2Boost: Very Fast Vertical Federated Gradient Boosting for Cross-Enterprise Learning	2021	SIGMOD	9.4090198e-05
3,166	LDP-IDS: Local Differential Privacy for Infinite Data Streams	2022	SIGMOD	7.6752517e-05
3,237	BlindFL: Vertical Federated Machine Learning without Peeking into Your Data	2022	SIGMOD	7.6089416e-05
4,930	IncShrink: Architecting Efficient Outsourced Databases using Incremental MPC and Differential Privacy	2022	SIGMOD	6.4402718e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,411	FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning	2023	SIGMOD
2	6,353	Differentially Private Vertical Federated Clustering	2023	VLDB
3	6,406	Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy	2022	VLDB
4	11,462	Federated Calibration and Evaluation of Binary Classifiers	2023	VLDB
5	11,252	Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy	2024	VLDB
6	4,185	Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics	2017	SIGMOD
7	11,438	Olive: Oblivious Federated Learning on Trusted Execution Environment Against the Risk of Sparsification	2023	VLDB
8	3,237	BlindFL: Vertical Federated Machine Learning without Peeking into Your Data	2022	SIGMOD
9	8,456	Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs	2024	VLDB
10	4,446	Projected Federated Averaging with Heterogeneous Differential Privacy	2022	VLDB