Privacy in Neural Network Learning: Threats and Countermeasures
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Algorithmic breakthroughs, the feasibility of collecting huge amount of data, and increasing computational power, contribute to the remarkable achievements of NNs. In particular, since Deep Neural Network (DNN) learning presents astonishing results in speech and image recognition, the amount of sophisticated applications based on it has exploded. However, the increasing number of instances of privacy leakage has been reported, and the corresponding severe consequences have caused great worry in this area. In this article, we focus on privacy issues in NN learning. First, we identify the privacy threats during NN training, and present privacy-preserving training schemes in terms of using centralized and distributed approaches. Second, we consider the privacy of prediction requests, and discuss the privacy-preserving protocols for NN prediction. We also analyze the privacy vulnerabilities of trained models. Three types of attacks on private information embedded in trained NN models are discussed, and a differential privacy-based solution is introduced.
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
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 2×
“[14] observed that machine learning models tend to behave differently on their training data versus those they never “met” before, which might because of overfitting.”
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 2×
“[6] considered local gradients from one participant in each update as a private vector, and designed a protocol to compute the sum of gradient vectors from different participants in a secure fashion.”
BackgroundModel Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961
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 2×
“Shmatikov [3] presented the concept of collaborative deep learning as a way to protect the privacy of training datasets.”
BackgroundSecureML: A System for Scalable Privacy-Preserving Machine Learning
Mohassel, P., & Zhang, Y. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.12 · Cited by 1,936 · cited 3×
“[5] Protecting training data Distributing private data among two servers to train models using secure”
MethodInfluentialDeep 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×
“[2] devised an attack on a collaborative deep learning procedure launched by its participants.”
BackgroundStealing Machine Learning Models via Prediction APIs
Tramèr, F., Zhang, F., Juels, A., Reiter, M. K., & Ristenpart, T. (2016) · arXiv · doi:10.48550/arxiv.1609.02943 · Cited by 796 · cited 2×
“[15] demonstrated that, if confidence values are available, launching model extraction attacks against NNs is equal to solving non-linear equation systems in weights, which refers to gradient descent-based optimizations.”
Background
Cited by
Differential Privacy for Deep and Federated Learning: A Survey
Ouadrhiri, A. E., & Abdelhadi, A. (2022) · IEEE Access · doi:10.1109/access.2022.3151670 · Cited by 445
“Chang et al. [47] present a summary of privacy issues in DL.”
BackgroundA review of privacy-preserving techniques for deep learning
Boulemtafes, A., Derhab, A., & Challal, Y. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.11.041 · Cited by 211
“In the literature, there are two related surveys [9, 10] that deal with privacy-preserving in deep learning.”
BackgroundSurvey: Leakage and Privacy at Inference Time
Jegorova, M., Kaul, C., Mayor, C., O'Neil, A. Q., Weir, A., Murray-Smith, R., & Tsaftaris, S. A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3229593 · Cited by 77
Compressive Privacy Generative Adversarial Network
Tseng, B.-W., & Wu, P.-Y. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.2968188 · Cited by 48
A comprehensive survey and taxonomy on privacy-preserving deep learning
Tran, A.-T., Luong, T.-D., & Huynh, V.-N. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127345 · Cited by 21
Metadata
- Authors
- Chang, S., & Li, C.
- Venue
- IEEE Network
- Published
- 2018-07
- Volume
- 32
- Issue
- 4
- Pages
- 61-67
- ISSN
- 0890-8044 (ISSN-L)
- 1558-156X
- OpenAlex
- W2886253048
- Cited by
- 36
- References
- 7
- FWCI
- 2.12
- Type
- journal article
- 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.