The DOI matches its Crossref record; 211 of the 211 references it cites were found in a registry or an index.
Privacy and Security Issues in Deep Learning: A Survey
Open accessAbstract
Deep Learning (DL) algorithms based on artificial neural networks have achieved remarkable success and are being extensively applied in a variety of application domains, ranging from image classification, automatic driving, natural language processing to medical diagnosis, credit risk assessment, intrusion detection. However, the privacy and security issues of DL have been revealed that the DL model can be stolen or reverse engineered, sensitive training data can be inferred, even a recognizable face image of the victim can be recovered. Besides, the recent works have found that the DL model is vulnerable to adversarial examples perturbed by imperceptible noised, which can lead the DL model to predict wrongly with high confidence. In this paper, we first briefly introduces the four types of attacks and privacy-preserving techniques in DL. We then review and summarize the attack and defense methods associated with DL privacy and security in recent years. To demonstrate that security threats really exist in the real world, we also reviewed the adversarial attacks under the physical condition. Finally, we discuss current challenges and open problems regarding privacy and security issues in DL.
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
Items 201–211 of 211
Consensus Convolutional Sparse Coding
Choudhury, B., Swanson, R., Heide, F., Wetzstein, G., & Heidrich, W. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.459 · Cited by 42
Adversarial Examples Versus Cloud-based Detectors: A Black-box Empirical Study
Li, X., Ji, S., Han, M., Ji, J., Ren, Z., Liu, Y., & Wu, C. (2019) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2019.2943467 · Cited by 42
Note on Attacking Object Detectors with Adversarial StickersPreprint
Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Song, D. X., Kohno, T., Rahmati, A., Prakash, A., & Tramèr, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.08062 · Cited by 40
Generating Differentially Private Datasets Using GANsPreprint
Triastcyn, A., & Faltings, B. V. (2018) · arXiv (Cornell University) · Cited by 36
Lightning-fast and privacy-preserving outsourced computation in the cloud
Liu, X., Deng, R. H., Wu, P., & Yang, Y. (2020) · Cybersecurity · doi:10.1186/s42400-020-00057-3 · Cited by 23
Self-citationFeaturized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic InferencePreprint
Bao, R., Liang, S., & Wang, Q. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07862 · Cited by 17
Zhang, T., & Zhu, Q. (2016) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/2996758.2996762 · Cited by 16
Image Transformation can make Neural Networks more robust against Adversarial ExamplesPreprint
Thang, D. D., & Matsui, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.03037 · Cited by 16
Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness
Liu, C., & JáJá, J. F. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/415 · Cited by 14
On-the-Fly Multiparty Computation on the Cloud via Multikey Fully Homomorphic Encryption.
López-Alt, A., Tromer, E., & Vaikuntanathan, V. (2013) · Cited by 11
Efficient Two-Step Adversarial Defense for Deep Neural NetworksPreprint
Chang, T.-J., He, Y., & Li, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.03739 · Cited by 10
Cited by
An Overview of Artificial Intelligence Ethics
Huang, C., Zhang, Z., Mao, B., & Yao, X. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3194503 · Cited by 482
A Survey of Privacy Attacks in Machine Learning
Rigaki, M., & Garcia, S. (2024) · ACM Computing Surveys · doi:10.1145/3624010 · Cited by 285
Akter, M., Moustafa, N., Lynar, T., & Razzak, I. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3192648 · Cited by 128
A Survey of Privacy Risks and Mitigation Strategies in the Artificial Intelligence Life Cycle
Shahriar, S., Allana, S., Hazratifard, S. M., & Dara, R. (2023) · IEEE Access · doi:10.1109/access.2023.3287195 · Cited by 114
Split Federated Learning for 6G Enabled-Networks: Requirements, Challenges, and Future Directions
Hafi, H., Brik, B., Frangoudis, P. A., Ksentini, A., & Bagaa, M. (2024) · IEEE Access · doi:10.1109/access.2024.3351600 · Cited by 90
Metadata
- Authors
- Liu, X., Xie, L., Wang, Y., Zou, J., Xiong, J., Ying, Z., & Vasilakos, A. V.
- Venue
- IEEE Access
- Published
- 2021
- Volume
- 9
- Pages
- 4566-4593
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3112787034
- Cited by
- 282
- References
- 211
- FWCI
- 12.98
- Type
- journal article
- Language
- en
- Open access
- gold
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.