LoMar: A Local Defense Against Poisoning Attack on Federated Learning
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Federated learning (FL) provides a high efficient decentralized machine learning framework, where the training data remains distributed at remote clients in a network. Though FL enables a privacy-preserving mobile edge computing framework using IoT devices, recent studies have shown that this approach is susceptible to poisoning attacks from the side of remote clients. To address the poisoning attacks on FL, we provide atwo-phasedefense algorithm called${\underline{Lo}cal\ \underline{Ma}licious\ Facto\underline{r}}$(LoMar). In phase I, LoMar scores model updates from each remote client by measuring the relative distribution over their neighbors using a kernel density estimation method. In phase II, an optimal threshold is approximated to distinguish malicious and clean updates from a statistical perspective. Comprehensive experiments on four real-world datasets have been conducted, and the experimental results show that our defense strategy can effectively protect the FL system. Specifically, the defense performance on Amazon dataset under a label-flipping attack indicates that, compared with FG+Krum, LoMar increases the target label testing accuracy from$96.0\%$to$98.8\%$, and the overall averaged testing accuracy from$90.1\%$to$97.0\%$.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Douceur, J. R. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-45748-8_24 · Cited by 4,419 · cited 1×
“FoolsGold(FG) [8] is a defense method against sybil attacks [32].”
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
VGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
Exploiting Unintended Feature Leakage in Collaborative Learning
Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00029 · Cited by 1,734
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · cited 1×
“The other one is to change the worst-case loss from a given attack strategy [51], [52], [53].”
BackgroundHow to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495 · cited 3×
“manipulate the training dataset in FL system in two ways: label vector manipulation [7] and input matrix manipulation [4].”
BackgroundMethodPoisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Yin, D., Chen, Y., Ramchandran, K., & Bartlett, P. (2018) · arXiv · doi:10.48550/arxiv.1803.01498 · Cited by 1,130 · cited 8×
“Trim Mean [12] method achieves the goal by finding a subset of training dataset to minimize the loss function.”
BackgroundMethodInfluentialData Poisoning Attacks Against Federated Learning Systems
Tolpegin, V., Truex, S., Gursoy, M. E., & Liu, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58951-6_24 · Cited by 927
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
Jagielski, M., Oprea, A., Biggio, B., Liu, C., Nita-Rotaru, C., & Li, B. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00057 · Cited by 861
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
Fang, M., Cao, X., Jia, J., & Gong, N. Z. (2019) · arXiv · doi:10.48550/arxiv.1911.11815 · Cited by 828 · cited 4×
“Recent studies [4], [5], [6], [8], [9], [10], [17], [45] on data poisoning attacks explore the”
BackgroundInfluentialThe Hidden Vulnerability of Distributed Learning in Byzantium
Mhamdi, E. M. E., Guerraoui, R., & Rouault, S. (2018) · arXiv · doi:10.48550/arxiv.1802.07927 · Cited by 648
SoK: Security and Privacy in Machine Learning
Papernot, N., McDaniel, P., Sinha, A., & Wellman, M. P. (2018) · 2018 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2018.00035 · Cited by 502 · cited 1×
“In targeted poisoning attacks, the ML system is forced to output a particular target class designed by the attacker [44].”
BackgroundVariable Kernel Estimates of Multivariate Densities
Breiman, L., Meisel, W., & Purcell, E. (1977) · Technometrics · doi:10.1080/00401706.1977.10489521 · Cited by 488 · cited 1×
“Previous studies [22], [23] have shown that the k-nearest neighborhood mapping is adaptive to estimate the local sample density from the distance perspective.”
ResultMitigating Sybils in Federated Learning Poisoning
Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2018) · arXiv · doi:10.48550/arxiv.1808.04866 · Cited by 385
Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners
Mei, S., & Zhu, X. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9569 · Cited by 346 · cited 1×
“The other one is to change the worst-case loss from a given attack strategy [51], [52], [53].”
BackgroundPoisonGAN: Generative Poisoning Attacks Against Federated Learning in Edge Computing Systems
Zhang, J., Chen, B., Cheng, X., Binh, H. T. T., & Yu, S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3023126 · Cited by 291
A uror: defending against poisoning attacks in collaborative deep learning systems
Shen, S., Tople, S., & Saxena, P. (2016) · Proceedings of the 32nd Annual Conference on Computer Security Applications · doi:10.1145/2991079.2991125 · Cited by 228
Casting out Demons: Sanitizing Training Data for Anomaly Sensors
Cretu, G. F., Stavrou, A., Locasto, M. E., Stolfo, S. J., & Keromytis, A. D. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.11 · Cited by 226 · cited 1×
“defenses [15], [47], [48], [49], [50] detects the poisoning data based on a negative impact of the learning model.”
BackgroundMitigating Poisoning Attacks on Machine Learning Models: A Data Provenance Based Approach
Baracaldo, N., Chen, B., Ludwig, H., & Safavi, J. A. (2017) · Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3128572.3140450 · Cited by 108 · cited 1×
“type of existing mechanisms [11], [12], [13], [14] is to detect malicious updates based on euclidean distances or angle differences between each pair of remote updates [8], [15].”
BackgroundFree-rider attacks on model aggregation in federated learning
Fraboni, Y., Vidal, R., & Lorenzi, M. (2020) · arXiv · doi:10.48550/arxiv.2006.11901 · Cited by 97
Cited by
Rodríguez-Barroso, N., Jiménez-López, D., Luzón, M. V., Herrera, F., & Martínez-Cámara, E. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.011 · Cited by 296
Poisoning attacks in federated learning: A survey
Xia, G., Chen, J., Yu, C., & Ma, J. (2023) · IEEE Access · doi:10.1109/access.2023.3238823 · Cited by 212
A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy
Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024) · Future Internet · doi:10.3390/fi16100374 · Cited by 58
Data-Agnostic Model Poisoning Against Federated Learning: A Graph Autoencoder Approach
Li, K., Zheng, J., Yuan, X., Ni, W., Akan, O. B., & Poor, H. V. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3362147 · Cited by 41
Privacy preserving and secure robust federated learning: A survey
Han, Q., Lu, S., Wang, W., Qu, H., Li, J., & Gao, Y. (2024) · Concurrency and Computation: Practice and Experience · doi:10.1002/cpe.8084 · Cited by 29
Metadata
- Authors
- Li, X., Qu, Z., Zhao, S., Tang, B., Lu, Z., & Liu, Y.
- Venue
- IEEE Transactions on Dependable and Secure Computing
- Published
- 2023-01-01
- Volume
- 20
- Issue
- 1
- Pages
- 437-450
- ISSN
- 1545-5971 (ISSN-L)
- 1941-0018
- 2160-9209
- OpenAlex
- W4285554319
- Cited by
- 149
- References
- 22
- FWCI
- 6.88
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.