Poisoning Attack in Federated Learning using Generative Adversarial Nets
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Federated learning is a novel distributed learning framework, where the deep learning model is trained in a collaborative manner among thousands of participants. The shares between server and participants are only model parameters, which prevent the server from direct access to the private training data. However, we notice that the federated learning architecture is vulnerable to an active attack from insider participants, called poisoning attack, where the attacker can act as a benign participant in federated learning to upload the poisoned update to the server so that he can easily affect the performance of the global model. In this work, we study and evaluate a poisoning attack in federated learning system based on generative adversarial nets (GAN). That is, an attacker first acts as a benign participant and stealthily trains a GAN to mimic prototypical samples of the other participants' training set which does not belong to the attacker. Then these generated samples will be fully controlled by the attacker to generate the poisoning updates, and the global model will be compromised by the attacker with uploading the scaled poisoning updates to the server. In our evaluation, we show that the attacker in our construction can successfully generate samples of other benign participants using GAN and the global model performs more than 80% accuracy on both poisoning tasks and main tasks.
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
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956 · cited 1×
“We notice that it is possible to construct the poisoning attack in federated learning for the following reasons [6]: 1) there are plenty of participants in federated learning system, it is most likely contains one or more malicious users; 2) since the participants’ local data and training process are invisible to the…”
BackgroundPrivacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 1×
“The main purpose of federated learning is to build a joint machine learning model upon localized datasets while providing privacy guarantee, which is an attractive technique for numerous emerging scenarios, such as edge computing and crowdsourced system [3], [4].”
BackgroundExploiting 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
Privacy-Preserving Deep Learning via Additively Homomorphic Encryption
Phong, L. T., Aono, Y., Hayashi, T., Wang, L., & Moriai, S. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2787987 · Cited by 1,662
How 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×
“Such invisibility property would introduce a severe security threat – poisoning attack [6]–[8].”
BackgroundMethodDeep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377 · cited 2×
“Inspired by [20], to mimic samples from another participants”
BackgroundMethodPoisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Chen, X., Liu, C., Li, B., Lu, K., & Song, D. (2017) · arXiv · doi:10.48550/arxiv.1712.05526 · Cited by 1,039
Cited by
A review of applications in federated learning
Li, L., Fan, Y., Tse, M., & Lin, K.-Y. (2020) · Computers & Industrial Engineering · doi:10.1016/j.cie.2020.106854 · Cited by 1,559
A survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480
Federated Learning for intrusion detection system: Concepts, challenges and future directions
Agrawal, S., Sarkar, S., Aouedi, O., Yenduri, G., Piamrat, K., Alazab, M., Bhattacharya, S., Maddikunta, P. K. R., & Gadekallu, T. R. (2022) · Computer Communications · doi:10.1016/j.comcom.2022.09.012 · Cited by 457
Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues
Du, Z., Wu, C., Yoshinaga, T., Yau, K.-L. A., Ji, Y., & Li, J. (2020) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2020.2992630 · Cited by 393
“[75] propose a poisoning attack against FL systems based on GAN.”
BackgroundDataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Goldblum, M., Tsipras, D., Xie, C., Chen, X., Schwarzschild, A., Song, D., Madry, A., Li, B., & Goldstein, T. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3162397 · Cited by 362
“Others instead opt for GAN-generated targeted poisons [69].”
BackgroundRodríguez-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
PoisonGAN: 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
“The main idea of launching poisoning attacks in federated learning is that the attacker generates poisoned updates via local model to impact the global parameters such that the global model will indirectly learn the attacker-chosen patterns from the crafted poison training data [13], [14].”
BackgroundSelf-citationVulnerabilities in federated learning
Bouacida, N., & Mohapatra, P. (2021) · IEEE Access · doi:10.1109/access.2021.3075203 · Cited by 248
“For instance, authors in [78] demonstrate how GAN can be used to get training samples through inference and use these recovered samples to poison the training data.”
BackgroundWild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
Cinà, A. E., Grosse, K., Demontis, A., Vascon, S., Zellinger, W., Moser, B. A., Oprea, A., Biggio, B., Pelillo, M., & Roli, F. (2023) · ACM Computing Surveys · doi:10.1145/3585385 · Cited by 152
Romoa: Robust Model Aggregation for the Resistance of Federated Learning to Model Poisoning Attacks
Mao, Y., Yuan, X., Zhao, X., & Zhong, S. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-88418-5_23 · Cited by 48
Wen, H., Wu, Y., Yang, C., Duan, H., & Yu, S. (2020) · IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps50562.2020.9162672 · Cited by 41
“Thirdly, considering the complexity of user identities, potential malicious devices, called Byzantine devices, hide behind benign edge devices and exhibit malicious behavior, such as poisoning attacks [8].”
BackgroundSelf-citationData-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
Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey
Wang, Z., Kang, Q., Zhang, X., & Hu, Q. (2022) · 2022 IEEE Wireless Communications and Networking Conference (WCNC) · doi:10.1109/wcnc51071.2022.9771619 · Cited by 41
Papadopoulos, C., Kollias, K.-F., & Fragulis, G. F. (2024) · Future Internet · doi:10.3390/fi16110415 · Cited by 35
“FL faces risks from adversarial attacks [52,53].”
Federated learning vulnerabilities, threats and defenses: A systematic review and future directions
Almutairi, S., & Barnawi, A. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100947 · Cited by 35
Privacy-Preserving Federated Learning with Resource Adaptive Compression for Edge Devices
Hidayat, M. A., Nakamura, Y., & Arakawa, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3347552 · Cited by 29
“Additionally, specific attacks can be inferred against FL, as demonstrated in [16], [17], [18], and [19].”
BackgroundOn Cooperative Federated Defense to Secure Multiaccess Edge Computing
Sedjelmaci, H., & Ansari, N. (2024) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2022.3167527 · Cited by 16
Exploring Adversarial Graph Autoencoders to Manipulate Federated Learning in The Internet of Things
Li, K., Yuan, X., Zheng, J., Ni, W., & Guizani, M. (2023) · 2023 International Wireless Communications and Mobile Computing (IWCMC) · doi:10.1109/iwcmc58020.2023.10183217 · Cited by 8
Metadata
- Authors
- Zhang, J., Chen, J., Wu, D., Chen, B., & Yu, S.
- Venue
- 2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE)
- Publisher
- IEEE
- Published
- 2019-08
- Pages
- 374-380
- OpenAlex
- W2982302101
- Cited by
- 197
- References
- 14
- FWCI
- 7.91
- Type
- conference paper
- Language
- en
- Open access
- closed
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.