Learning from Differentially Private Neural Activations with Edge Computing
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Deep convolutional neural networks (DNNs) have brought significant performance improvements to face recognition. However the training can hardly be carried out on mobile devices because the training of these models requires much computational power. An individual user with the demand of deriving DNN models from her own datasets usually has to outsource the training procedure onto an edge server. However this outsourcing method violates privacy because it exposes the users' data to curious service providers. In this paper, we utilize the differentially private mechanism to enable the privacy-preserving edge based training of DNN face recognition models. During the training, DNN is split between the user device and the edge server in a way that both private data and model parameters are protected, with only a small cost of local computations. We rigorously prove that our approach is privacy preserving. We finally show that our mechanism is capable of training models in different scenarios, e.g., from scratch, or through fine-tuning over existed models.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2603342 · Cited by 6,214
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 · cited 4×
“Furthermore, a membership inference attack is reported in [11].”
BackgroundInfluentialA Discriminative Feature Learning Approach for Deep Face Recognition
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_31 · Cited by 4,077 · cited 2×
“Public face recognizing models such as [5], [7], [26], [8] have contributed a lot to accelerate development of both academia and industry.”
BackgroundPractical 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 4×
“But user’s private data will be violated seriously if the central server is untrusted [1].”
BackgroundMethodInfluentialThe Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
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 7×
“Assuming that it’s possible for mobile devices to perform distributed training given powerful equipments like neural engines built in iPhone X and Tensorflow Lite training framework for mobile devices provided by Google, user’s private data will still be violated by an active adversary even with efficient privacy-pres…”
BackgroundMethodResultInfluentialDeep 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 3×
“Assuming that it’s possible for mobile devices to perform distributed training given powerful equipments like neural engines built in iPhone X and Tensorflow Lite training framework for mobile devices provided by Google, user’s private data will still be violated by an active adversary even with efficient privacy-pres…”
BackgroundBoosting and Differential Privacy
Dwork, C., Rothblum, G. N., & Vadhan, S. (2010) · 2010 IEEE 51st Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2010.12 · Cited by 784 · cited 1×
“Basically we encounter an adaptive composition situation suggested in Dwork’s boosting theory [25].”
MethodNot Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
Wang, J., Zhang, J., Bao, W., Zhu, X., Cao, B., & Yu, P. S. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220106 · Cited by 188
Cited by
Deep Learning With Edge Computing: A Review
Chen, J., & Ran, X. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2921977 · Cited by 1,540
Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices
Zhao, Y., Zhao, J., Jiang, L., Tan, R., Niyato, D., Li, Z., Lyu, L., & Liu, Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3017377 · Cited by 613
FEEL: A Federated Edge Learning System for Efficient and Privacy-Preserving Mobile Healthcare
Guo, Y., Liu, F., Cai, Z., Chen, L., & Xiao, N. (2020) · 49th International Conference on Parallel Processing - ICPP · doi:10.1145/3404397.3404410 · Cited by 52
Collaborative cloud-edge computation for personalized driving behavior modeling
Zhang, X., Qiao, M., Liu, L., Xu, Y., & Shi, W. (2019) · Proceedings of the 4th ACM/IEEE Symposium on Edge Computing · doi:10.1145/3318216.3363310 · Cited by 30
“Comparing with the traditional cloud-based approaches which upload all the data to a centralized cloud service, edge computing can reduce or minimize network latency [29, 30] and address privacy concerns [21].”
Background
Metadata
- Authors
- Mao, Y., Yi, S., Li, Q., Feng, J., Xu, F., & Zhong, S.
- Venue
- 2018 IEEE/ACM Symposium on Edge Computing (SEC)
- Publisher
- IEEE
- Published
- 2018-10
- Pages
- 90-102
- OpenAlex
- W2904819746
- Cited by
- 40
- References
- 10
- FWCI
- 2.18
- 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.