14.5.2.1 Privacy in Learning

Chapter Contents (Back)
Learning. Privacy.
See also Surveillance Systems, Privacy Protection, Issues, Techniques, Face Obscuration.
See also Biometrics, Privacy Issues, Security Issues.

Manju, S., Punithavalli, M.,
Neural network-based ideation learning for intelligent agents: e-brainstorming with privacy preferences,
IJCVR(5), No. 3, 2015, pp. 231-253.
DOI Link 1509
BibRef

Oneto, L.[Luca], Ridella, S.[Sandro], Anguita, D.[Davide],
Differential privacy and generalization: Sharper bounds with applications,
PRL(89), No. 1, 2017, pp. 31-38.
Elsevier DOI 1704
Differential privacy BibRef

González-Serrano, F.J.[Francisco-Javier], Navia-Vázquez, Á.[Ángel], Amor-Martín, A.[Adrián],
Training Support Vector Machines with privacy-protected data,
PR(72), No. 1, 2017, pp. 93-107.
Elsevier DOI 1708
Machine learning BibRef

Yang, J.J.[Jing-Jing], Wu, J.Z.[Jin-Zhao], Wang, X.J.[Xiao-Jing],
Special Issue Retraction: Convolutional neural network based on differential privacy in exponential attenuation mode for image classification,
IET-IPR(17), No. 1, January 2023, pp. 301.
DOI Link 2301
BibRef
And: IET-IPR(14), No. 15, 15 December 2020, pp. 3676-3681.
DOI Link 2103
Adding gaussian noise. BibRef

Kim, Y., Cho, D., Hong, S.,
Towards Privacy-Preserving Domain Adaptation,
SPLetters(27), 2020, pp. 1675-1679.
IEEE DOI 1806
Prototypes, Reliability, Adaptation models, Feature extraction, Data models, Data privacy, Training, Domain adaptation, class prototypes BibRef

Venkategowda, N.K.D.[Naveen K. D.], Werner, S.[Stefan],
Privacy-Preserving Distributed Maximum Consensus,
SPLetters(27), 2020, pp. 1839-1843.
IEEE DOI 2011
Privacy, Nickel, Signal processing algorithms, Optimization, Linear programming, Convex functions, Gaussian noise, ADMM, privacy BibRef

Alkhelaiwi, M.[Munirah], Boulila, W.[Wadii], Ahmad, J.[Jawad], Koubaa, A.[Anis], Driss, M.[Maha],
An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification,
RS(13), No. 11, 2021, pp. xx-yy.
DOI Link 2106
Privacy of data and results when using cloud services for deep learning. Train on encrypted data. BibRef

Luo, Y.[Yi], Feng, G.R.[Guo-Rui], Zhang, X.P.[Xin-Peng],
Hierarchical Authorization of Convolutional Neural Networks for Multi-User,
SPLetters(28), 2021, pp. 1560-1564.
IEEE DOI 2108
Authorization, Neural networks, Training, Mathematical model, Testing, Differential privacy, Watermarking, rights management BibRef

Yang, B.Y.[Bao-Yao], Yeh, H.W.[Hao-Wei], Harada, T.[Tatsuya], Yuen, P.C.[Pong C.],
Model-Induced Generalization Error Bound for Information-Theoretic Representation Learning in Source-Data-Free Unsupervised Domain Adaptation,
IP(31), 2022, pp. 419-432.
IEEE DOI 2112
BibRef
Earlier: A2, A1, A4, A3:
SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation,
WACV21(474-483)
IEEE DOI 2106
Adaptation models, Data models, Upper bound, Predictive models, Optimization, Computational modeling, Data privacy, representation learning. Training, Semantics, Predictive models, Gaussian distribution, Feature extraction BibRef

Yeh, H.W.[Hao-Wei], Meng, Q.[Qier], Harada, T.[Tatsuya],
Misalignment-Free Relation Aggregation for Multi-Source-Free Domain Adaptation,
OutDistri23(4315-4324)
IEEE DOI 2401
BibRef

Yeh, H.W.[Hao-Wei], Westfechtel, T.[Thomas], Huang, J.B.[Jia-Bin], Harada, T.[Tatsuya],
Boosting Source-free Domain Adaptation via Confidence-based Subsets Feature Alignment,
ICPR22(2857-2863)
IEEE DOI 2212
Adaptation models, Predictive models, Multitasking, Data models, Entropy, Pattern recognition, Reliability BibRef

Biswas, C.[Chandan], Ganguly, D.[Debasis], Mukherjee, P.S.[Partha Sarathi], Bhattacharya, U.[Ujjwal], Hou, Y.F.[Yu-Fang],
Privacy-aware supervised classification: An informative subspace based multi-objective approach,
PR(122), 2022, pp. 108301.
Elsevier DOI 2112
Privacy preserving representation learning, Informative subspace, Multi-objective learning, Defence against information stealing adversarial attacks BibRef

Bai, J.W.[Jia-Wang], Li, Y.M.[Yi-Ming], Li, J.W.[Jia-Wei], Yang, X.[Xue], Jiang, Y.[Yong], Xia, S.T.[Shu-Tao],
Multinomial random forest,
PR(122), 2022, pp. 108331.
Elsevier DOI 2112
Random forest, Consistency, Differential privacy, Classification BibRef


Ni, X.Y.[Xing-Yang], Huttunen, H.[Heikki], Rahtu, E.[Esa],
On the Importance of Encrypting Deep Features,
HTCV21(4125-4132)
IEEE DOI 2112
Data privacy, Codes, Computational modeling, Neural networks, Production BibRef

Yin, H.X.[Hong-Xu], Mallya, A.[Arun], Vahdat, A.[Arash], Alvarez, J.M.[Jose M.], Kautz, J.[Jan], Molchanov, P.[Pavlo],
See through Gradients: Image Batch Recovery via GradInversion,
CVPR21(16332-16341)
IEEE DOI 2111
Computation for deep networks. Training, Deep learning, Data privacy, Image matching, Estimation, Collaborative work, Pattern recognition BibRef

Singh, A.[Abhishek], Chopra, A.[Ayush], Garza, E.[Ethan], Zhang, E.[Emily], Vepakomma, P.[Praneeth], Sharma, V.[Vivek], Raskar, R.[Ramesh],
DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks,
CVPR21(12120-12130)
IEEE DOI 2111
Deep learning, Privacy, Face recognition, Collaboration, Medical services, Benchmark testing BibRef

Hanzlik, L.[Lucjan], Zhang, Y.[Yang], Grosse, K.[Kathrin], Salem, A.[Ahmed], Augustin, M.[Maximilian], Backes, M.[Michael], Fritz, M.[Mario],
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service,
TCV21(3295-3304)
IEEE DOI 2109
Data privacy, Computational modeling, Perturbation methods, Reverse engineering, Machine learning, Intellectual property, Data models BibRef

Zhu, F.[Fei], Zhang, X.Y.[Xu-Yao], Wang, C.[Chuang], Yin, F.[Fei], Liu, C.L.[Cheng-Lin],
Prototype Augmentation and Self-Supervision for Incremental Learning,
CVPR21(5867-5876)
IEEE DOI 2111
Training, Learning systems, Deep learning, Data privacy, Computational modeling, Prototypes BibRef

Choi, Y.[Yoojin], El-Khamy, M.[Mostafa], Lee, J.[Jungwon],
Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay,
CLVision21(3538-3547)
IEEE DOI 2109
Data privacy, Training data, Data models, Pattern recognition, Knowledge transfer BibRef

Reed, C.J.[Colorado J.], Metzger, S.[Sean], Srinivas, A.[Aravind], Darrell, T.J.[Trevor J.], Keutzer, K.[Kurt],
SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning,
CVPR21(2673-2682)
IEEE DOI 2111
Training, Data privacy, Correlation, Image recognition, Network architecture, Pattern recognition BibRef

Kurmi, V.K.[Vinod K.], Subramanian, V.K.[Venkatesh K.], Namboodiri, V.P.[Vinay P.],
Domain Impression: A Source Data Free Domain Adaptation Method,
WACV21(615-625)
IEEE DOI 2106
Adaptation models, Data privacy, Analytical models, Computational modeling, Memory management BibRef

Ahmed, S.M.[Sk Miraj], Raychaudhuri, D.S.[Dripta S.], Paul, S.[Sujoy], Oymak, S.[Samet], Roy-Chowdhury, A.K.[Amit K.],
Unsupervised Multi-source Domain Adaptation Without Access to Source Data,
CVPR21(10098-10107)
IEEE DOI 2111
Training, Adaptation models, Data privacy, Predictive models, Benchmark testing, Data models BibRef

Kundu, J.N.[Jogendra Nath], Venkat, N.[Naveen], Revanur, A.[Ambareesh], Rahul, M.V., Babu, R.V.[R. Venkatesh],
Towards Inheritable Models for Open-Set Domain Adaptation,
CVPR20(12373-12382)
IEEE DOI 2008
Adaptation models, Task analysis, Data models, Predictive models, Computational modeling, Data privacy, Training BibRef

Sarpatwar, K., Ratha, N., Nandakumar, K., Shanmugam, K., Rayfield, J.T., Pankanti, S., Vaculin, R.,
Privacy Enhanced Decision Tree Inference,
TCV20(154-159)
IEEE DOI 2008
Decision trees, Privacy, Machine learning, Encryption, Data models, Data privacy BibRef

Wu, Z.Y.[Zhen-Yu], Wang, Z.Y.[Zhang-Yang], Wang, Z.W.[Zhao-Wen], Jin, H.L.[Hai-Lin],
Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study,
ECCV18(XVI: 627-645).
Springer DOI
WWW Link. 1810

See also Privacy-Preserving Visual Recognition PA-HMDB51. BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Meta-Learning .


Last update:Mar 16, 2024 at 20:36:19