Differential Privacy Federated Learning Based on Adaptive Adjustment
Source abstract
Abstract
Federated learning effectively alleviates privacy and security issues raised by the development of artificial intelligence through a distributed training architecture. Existing research has shown that attackers can compromise... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Multimodal federated learning: concept, methods, applications and future directions10.1016/j.inffus.2024.102576 ↗
2. A quantum federated learning framework for classical clients
3. When edge meets learning: adaptive control for resource-constrained distributed machine learning
4. Exploring threats, defenses, and privacy-preserving techniques in federated learning: a survey10.1109/MC.2023.3324975 ↗
5. Federated learning in mobile edge networks: a comprehensive survey10.1109/COMST.2020.2986024 ↗
6. Unleashing the prospective of blockchain-federated learning fusion for IoT security: a comprehensive review10.1016/j.cosrev.2024.100685 ↗
7. The algorithmic foundations of differential privacy10.1561/0400000042 ↗
8. Deep learning with differential privacy
9. Understanding clipping for federated learning: convergence and client-level differential privacy
10. Securing distributed SGD against gradient leakage threats10.1109/TPDS.2023.3273490 ↗
11. Differentially private federated learning with an adaptive noise mechanism10.1109/TIFS.2023.3318944 ↗
12. Adap DP-FL: differentially private federated learning with adaptive noise
13. Local differential privacy federated learning based on heterogeneous data multi-privacy mechanism10.1016/j.comnet.2024.110822 ↗
14. Federated learning with differential privacy via fast fourier transform for tighter-efficient combining10.1038/s41598-024-77428-0 ↗
15. Efficient federated learning privacy preservation method with heterogeneous differential privacy10.1016/j.cose.2024.103715 ↗
16. Differentially private federated learning on non-iid data: convergence analysis and adaptive optimization10.1109/TKDE.2024.3379001 ↗
17. Communication-efficient learning of deep networks from decentralized data
18. Practical secure aggregation for privacy-preserving machine learning
19. Flamingo: multi-round single-server secure aggregation with applications to private federated learning
20. Phong · Applications and techniques in information security · 100
21. Hu R, Gong Y, Guo Y. Federated learning with sparsification-amplified privacy and adaptive optimization. arXiv preprint arXiv:2008.01558. 2020.10.24963/ijcai.2021/202 ↗
22. CLFLDP: communication-efficient layer clipping federated learning with local differential privacy10.1016/j.sysarc.2024.103067 ↗
23. A differential privacy federated learning scheme based on adaptive gaussian noise
24. Differential privacy: a survey of results
25. A differentially private framework for deep learning with convexified loss functions10.1109/TIFS.2022.3169911 ↗
26. Heterogeneous gaussian mechanism: preserving differential privacy in deep learning with provable robustness
27. Do not let privacy overbill utility: gradient embedding perturbation for private learning
28. Adaptive laplace mechanism: differential privacy preservation in deep learning
29. Trade-off between privacy and accuracy in resilient vector consensus
30. McMahan HB, Ramage D, Talwar K, Zhang L. Learning differentially private recurrent language models. arXiv preprint arXiv:1710.06963. 2017.
31. Differentially private federated learning on heterogeneous data
32. PPeFL: privacy-preserving edge federated learning with local differential privacy
33. Privacy-preserving federated learning based on differential privacy and momentum gradient descent
34. PLDP-FL: federated learning with personalized local differential privacy10.3390/e25030485 ↗
35. Malekmohammadi · Noise-aware algorithm for heterogeneous differentially private federated learning · 2024 · 34461
36. McMahan HB, Moore E, Ramage D, y Arcas BA. Federated learning of deep networks using model averaging. arXiv preprint arXiv:1602.05629v1. 2016.
37. Mironov I, Talwar K, Zhang L. Rényi differential privacy of the sampled gaussian mechanism. arXiv preprint arXiv:1908.10530. 2019.
38. Rényi differential privacy
39. Zhou Y, Liu X, Fu Y, Wu D, Li C, Yu S. Optimizing the numbers of queries and replies in federated learning with differential privacy. arXiv preprint arXiv:2107.01895. 2021.
40. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
41. Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. 2017. doi:10.48550/arXiv.1708.07747.
42. Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. In: Handbook of systemic autoimmune diseases; 2009.
43. Caldas S, Duddu SMK, Wu P, Li T, Konečnỳ J, McMahan HB, et al. LEAF: a benchmark for federated settings. arXiv preprint arXiv:1812.01097. 2018.
44. The distributed discrete gaussian mechanism for federated learning with secure aggregation