The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Unleashing the Tiger: Inference Attacks on Split Learning
Open accessAbstract
We investigate the security of split learning---a novel collaborative machine learning framework that enables peak performance by requiring minimal resource consumption. In the present paper, we expose vulnerabilities of the protocol and demonstrate its inherent insecurity by introducing general attack strategies targeting the reconstruction of clients' private training sets. More prominently, we show that a malicious server can actively hijack the learning process of the distributed model and bring it into an insecure state that enables inference attacks on clients' data. We implement different adaptations of the attack and test them on various datasets as well as within realistic threat scenarios. We demonstrate that our attack can overcome recently proposed defensive techniques aimed at enhancing the security of the split learning protocol. Finally, we also illustrate the protocol's insecurity against malicious clients by extending previously devised attacks for Federated Learning.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754
Tschandl, P., Rosendahl, C., & Kittler, H. (2018) · Scientific Data · doi:10.1038/sdata.2018.161 · Cited by 3,628
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · cited 1×
“Here, we report additionally results for the dataset Fashion-MNIST [41], CelebA [31] and Omniglot [29].”
ResultMeasuring and testing dependence by correlation of distances
Székely, G. J., Rizzo, M. L., & Bakirov, N. K. (2007) · The Annals of Statistics · doi:10.1214/009053607000000505 · Cited by 2,684
Codella, N. C. F., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., et al. (2018) · 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) · doi:10.1109/isbi.2018.8363547 · Cited by 2,620
Privacy-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×
“Distributed (also collaborative [34]) machine learning allows a set of remote clients C = {21, .”
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
Bulat, A., & Tzimiropoulos, G. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.116 · Cited by 1,464
Deep 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
Self-citationLocal 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
Efficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence
Hao, M., Li, H., Luo, X., Xu, G., Yang, H., & Liu, S. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2945367 · Cited by 569 · cited 1×
“Accordingly, variants of federated learning have been proposed to reduce the effectiveness of those attacks [22, 23, 30, 34], but they achieved only limited results.”
Split learning for health: Distributed deep learning without sharing raw patient data
Vepakomma, P., Gupta, O., Swedish, T., & Raskar, R. (2018) · arXiv · doi:10.48550/arxiv.1812.00564 · Cited by 513
Ganju, K., Wang, Q., Yang, W., Gunter, C. A., & Borisov, N. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243834 · Cited by 475 · cited 1×
“This form of inference was introduced in [7] and extended to neural networks in [18].”
BackgroundHIPAA regulations - a new era of medical-record privacy?
Annas, G. J. (2003) · New England Journal of Medicine · doi:10.1056/nejmlim035027 · Cited by 402 · cited 1×
“For instance, hospitals cannot share patients’ data with external entities due to regulations such as HIPAA [6].”
BackgroundModel inversion attacks against collaborative inference
He, Z., Zhang, T., & Lee, R. B. (2019) · Proceedings of the 35th Annual Computer Security Applications Conference · doi:10.1145/3359789.3359824 · Cited by 313 · cited 1×
“This assumption is congruent with previous attacks against collaborative inference [29], and makes our threat model more realistic and less restrictive than the ones adopted in other related works [55, 58], where the adversary is assumed to have direct access to leaked pairs of smashed data and private data.”
ResultEnd-to-End Evaluation of Federated Learning and Split Learning for Internet of Things
Gao, Y., Kim, M., Abuadbba, S., Kim, Y., Thapa, C., Kim, K., Camtep, S. A., Kim, H., & Nepal, S. (2020) · 2020 International Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds51746.2020.00017 · Cited by 240
Detailed comparison of communication efficiency of split learning and federated learning
Singh, A., Vepakomma, P., Gupta, O., & Raskar, R. (2019) · arXiv · doi:10.48550/arxiv.1909.09145 · Cited by 148
Cited by
ShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated Learning
Ma, Z., Ma, J., Miao, Y., Li, Y., & Deng, R. H. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3169918 · Cited by 371
Split Learning Over Wireless Networks: Parallel Design and Resource Management
Wu, W., Li, M., Qu, K., Zhou, C., Shen, X., Zhuang, W., Li, X., & Shi, W. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3242704 · Cited by 278
A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning
Tian, Z., Cui, L., Liang, J., & Yu, S. (2023) · ACM Computing Surveys · doi:10.1145/3551636 · Cited by 271
Metadata
- Authors
- Pasquini, D., Ateniese, G., & Bernaschi, M.
- Venue
- Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2021-11-12
- Pages
- 2113-2129
- OpenAlex
- W3111351313
- Cited by
- 163
- References
- 21
- FWCI
- 11.97
- Type
- conference paper
- 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.