Multi-Robot Privacy-Preserving Algorithms Based on Federated Learning: A Review
Source abstract
Abstract
The robotics industry has seen rapid development in recent years due to the Corona Virus Disease 2019. With the development of sensors and smart devices, factories and enterprises have accumulated a large amount of data in their daily production, which creates extremely favorable conditions for robots to perform machine learning. However, in recent years, people’s awareness of data privacy has been increasing, leading to the inability to circulate data between different enterprises, resulting in the emergence of data silos. The emergence of federated learning provides a feasible solution to this problem, and the combination of federated learning and multi-robot systems can break down data silos and improve the overall performance of robots. However, as scholars have studied more deeply, they found that federated learning has very limited privacy protection. Therefore, how to protect data privacy from infringement remains an important issue. In this paper, we first give a brief introduction to the current development of multi-robot and federated learning; second, we review three aspects of privacy protection methods commonly used, privacy protection methods for multi-robot, and Other Problems Faced by Multi-robot Systems, focusing on method comparisons and challenges; and finally draw conclusions and predict possible future research directions.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Cryptography and Data Security · Mobile Crowdsensing and Crowdsourcing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (96)
Show source-provided references
1. Past, present, and future of aerial robotic manipulators10.1109/TRO.2021.3084395 ↗
2. Demining robots: Overview and mission strategy for landmine identification in the field
3. Coal mine rescue robots: Development, applications and lessons learned
4. Ferromagnetic climbing robot for industrial flaw detection: An implementation of computer vision
5. A survey on federated learning systems: Vision, hype and reality for data privacy and protection10.1109/TKDE.2021.3124599 ↗
6. Communication-efficient learning of deep networks from decentralized data
7. A review of applications in federated learning10.1016/j.cie.2020.106854 ↗
8. Federated learning in a medical context: A systematic literature review10.1145/3412357 ↗
9. A review of privacy-preserving federated learning for the Internet-of-Things10.1007/978-3-030-70604-3_2 ↗
10. A survey on security and privacy of federated learning10.1016/j.future.2020.10.007 ↗
11. Federated learning in smart cities: Privacy and security survey10.1016/j.ins.2023.03.033 ↗
12. Mission specification and decomposition for multi-robot systems10.1016/j.robot.2023.104386 ↗
13. Parallel decomposition and concurrent satisfaction for heterogeneous multi-robot task and motion planning under temporal logic specifications10.1007/s10626-021-00355-z ↗
14. Auctions for multi-robot task allocation in communication limited environments10.1007/s10514-019-09828-5 ↗
15. Cooperative multi-robot task allocation with teinforcement learning10.3390/app12010272 ↗
16. Online trajectory generation with distributed model predictive control for multi-robot motion planning10.1109/LRA.2020.2964159 ↗
17. Representation-optimal multi-robot motion planning using conflict-based search10.1109/LRA.2021.3068910 ↗
18. Federated machine learning: Concept and applications10.1145/3339474 ↗
19. Deep learning with differential privacy
20. Differential privacy for deep and federated learning: A survey10.1109/ACCESS.2022.3151670 ↗
21. Protocols for secure computations
22. How to share a secret10.1145/359168.359176 ↗
23. Safeguarding cryptographic keys
24. Transaction protection by beacons10.1016/0022-0000(83)90042-9 ↗
25. Privacy-preserving deep learning via additively homomorphic encryption10.1109/TIFS.2017.2787987 ↗
26. A survey on homomorphic encryption schemes: Theory and implementation10.1145/3214303 ↗
27. Fully homomorphic encryption using ideal lattices
28. PPFL: Privacy-preserving federated learning with trusted execution environments
29. Intel SGX explained
30. A survey on distributed machine learning10.1145/3377454 ↗
31. Privacy-preserving deep learning
32. Privacy-preserving distributed machine learning via local randomization and ADMM perturbation10.1109/TSP.2020.3009007 ↗
33. Toward secure and privacy-preserving distributed deep learning in fog-cloud computing10.1109/JIOT.2020.3012480 ↗
34. Reducing leakage in distributed deep learning for sensitive health data
35. CodedPrivateML: A fast and privacy-preserving framework for distributed machine learning10.1109/JSAIT.2021.3053220 ↗
36. Anonymous and efficient authentication scheme for privacy-preserving distributed learning10.1109/TIFS.2022.3181848 ↗
37. Privacy-preserving machine learning with homomorphic encryption and federated learning10.3390/fi13040094 ↗
38. PPFL: Privacy-preserving federated learning with trusted execution environments
39. Privacy-preserving blockchain-based federated learning for traffic flow prediction10.1016/j.future.2020.12.003 ↗
40. EPPDA: An efficient privacy-preserving data aggregation federated learning scheme
41. An adaptive federated learning scheme with differential privacy-preserving10.1016/j.future.2021.09.015 ↗
42. Privacy-preserving federated learning framework based on chained secure multiparty computing10.1109/JIOT.2020.3022911 ↗
43. GrCol-PPFL: User-based group collaborative federated learning privacy protection framework10.32604/cmc.2023.032758 ↗
44. Federated learning with differential privacy: Algorithms and performance analysis10.1109/TIFS.2020.2988575 ↗
45. Real-time cloud robotics in practical smart city applications
46. Federated learning in robotic and autonomous systems10.1016/j.procs.2021.07.041 ↗
47. Federated learning for vision-based obstacle avoidance in the Internet of Robotic Things
48. Privacy-preserving image multi-classification deep learning model in robot system of industrial IoT10.1007/s00521-020-05426-0 ↗
49. PDLHR: Privacy-preserving deep learning model with homomorphic re-encryption in robot system10.1109/JSYST.2021.3078637 ↗
50. Privacy-preserving multi-robot task allocation via secure multi-party computation
51. Privacy-preserving dynamic average consensus via state decomposition: Case study on multi-robot formation control10.1016/j.automatica.2022.110182 ↗
52. DiNNO: Distributed neural network qptimization for multi-robot collaborative learning10.1109/LRA.2022.3142402 ↗
53. Flow-FL: Data-driven federated learning for spatio-temporal predictions in multi-robot systems
54. Towards lifelong federated learning in autonomous mobile robots with continuous sim-to-real transfer10.1016/j.procs.2022.10.123 ↗
55. On decentralizing federated reinforcement learning in multi-robot scenarios
56. Efficient and privacy-enhanced federated learning for industrial artificial intelligence10.1109/TII.2019.2945367 ↗
57. SecMDGM: Federated learning security mechanism based on multi-dimensional auctions10.3390/s22239434 ↗
58. Decentralized P2P federated learning for privacy-preserving and resilient mobile robotic systems10.1109/MWC.004.2200381 ↗
59. Robot target recognition using deep federated learning10.1002/int.22606 ↗
60. FedPARL: Client activity and resource-oriented lightweight federated learning model for resource-constrained heterogeneous IoT environment10.3389/frcmn.2021.657653 ↗
61. Membership inference attacks against machine learning models
62. CS-MIA: Membership inference attack based on prediction confidence series in federated learning10.1016/j.jisa.2022.103201 ↗
63. A. Suri, P. Kanani, V. J. Marathe and D. W. Peterson, “Subject membership inference attacks in federated learning, arXiv:2206.03317v1, 2022.
64. ML-Leaks: Model and data independent membership inference attacks and defenses on machine learning models
65. Stolen memories: Levering model memorization for calibrated white-box membership inference
66. Exploiting unintended property leakage in blockchain-assisted federated learning for intelligent edge computing10.1109/JIOT.2020.3028110 ↗
67. Poisoning-assisted property inference attack against federated learning10.1109/TDSC.2022.3196646 ↗
68. Deep leakage from gradients
69. Grnn: Generative regression neural network—A data leakage attack for federated learning
70. Recover user's private training image data by gradient in federated learning10.3390/s22197157 ↗
71. B. Zhao, K. R. Mopuri and H. Bilen, “IDLG: Improved deep leakage from gradients, arXiv:2001.02610, 2020.
72. Inverting gradients-how easy is it to break privacy in federated learning?
73. R-GAP: Recursive gradient attack on privacy
74. See through gradients: Image batch recovery via gradinversion
75. Gradient inversion with generative image prior
76. CAFE: Catastrophic data leakage in vertical federated learning
77. E2EGI: End-to-End gradient inversion in federated learning10.1109/JBHI.2022.3204455 ↗
78. Y. X. Wen, J. Geiping, L. Fowl, M. Goldblu and T. Goldstein, “Fishing for user data in large-batch federated learning via gradient magnification, arXiv:2202.00580, 2022.
79. FastProtector: An efficient federal learning method supporting gradient privacy preservation
80. G-VCFL: Grouped verifiable chained privacy-preserving federated learning10.1109/TNSM.2022.3196404 ↗
81. Decentralized wireless federated learning with differential privacy10.1109/TII.2022.3145010 ↗
82. Privacy-preserving federated learning based on multi-key homomorphic encryption10.1002/int.22818 ↗
83. Secure aggregation in federated learning via multiparty homomorphic encryption
84. Privacy-preserving and communication-efficient federated learning in Internet of Things10.1016/j.cose.2021.102199 ↗
85. Privacy-preserving byzantine-robust federated learning10.1016/j.csi.2021.103561 ↗
86. Blockchain-empowered decentralized horizontal federated learning for 5G-enabled UAVs10.1109/TII.2021.3116132 ↗
87. When federated learning meets blockchain: A new distributed learning paradigm10.1109/MCI.2022.3180932 ↗
88. Security and privacy threats to federated learning: Issues, methods, and challenges
89. FedMCCS: Multicriteria client selection model for optimal IoT federated learning10.1109/JIOT.2020.3028742 ↗
90. FairFL: A fair federated learning approach to reducing demographic bias in privacy-sensitive classification models
91. Client selection for federated learning with Non-IID data in mobile edge computing10.1109/ACCESS.2021.3056919 ↗
92. FedCor: Correlation-based active client selection strategy for heterogeneous federated learning
93. PyramidFL: A fine-grained client selection framework for efficient federated learning
94. Grouped federated learning: A decentralized learning framework with low latency for heterogeneous devices
95. Client selection based weighted federated few-shot learning10.1016/j.asoc.2022.109488 ↗
96. HACCS: Heterogeneity-Aware clustered client selection for accelerated federated learning