: Email
: LinkdinFHE and Machine Learning References
Down these papers
Prediction Phase
————————————————————————————————
Logistic Regression
1. Bos J W, Lauter K, Naehrig M. Private Predictive Analysis On Encrypted Medical Data. Journal Of Biomedical Informatics, 2014, 50: 234-243.Neural Networks
1. Boemer F, Lao Y, Cammarota R, et al. nGraph-HE: A Graph Compiler For Deep Learning On Homomorphically Encrypted Data. arXiv preprint arXiv:1810.10121, 2018.2. Boemer F, Costache A, Cammarota R, et al. nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data. Proceedings of the 7th ACM Workshop on Encrypted Computing & Applied Homomorphic Cryptography. ACM, 2019: 45-56.
3. Gilad-Bachrach R, Dowlin N, Laine K, et al. Cryptonets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy. International Conference on Machine Learning. 2016: 201-210.
Convolutional Neural Networks
1. Hesamifard E, Takabi H, Ghasemi M. CryptoDL: Deep Neural Networks over Encrypted Data. ArXiv preprint:1711.05189, 2017.2. Hesamifard E, Takabi H, Ghasemi M. Deep Neural Networks Classification over Encrypted Data. Proceedings of the Ninth ACM Conference on Data and Application Security and Privacy. ACM, 2019: 97-108.
3. Brutzkus A, Elisha O, Gilad-Bachrach R. Low Latency Privacy Preserving Inference. ArXiv preprint arXiv:1812.10659, 2018.
4. Izabachène M, Sirdey R, Zuber M. Practical Fully Homomorphic Encryption for Fully Masked Neural Networks. International Conference on Cryptology and Network Security. Springer, Cham, 2019: 24-36.
5. Boddeti V N. Secure Face Matching Using Fully Homomorphic Encryption. IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS). IEEE, 2018: 1-10.
Model Training
————————————————————————————————
Logistic Regression
1. Kim A, Song Y, Kim M, et al. Logistic Regression Model Training Based On The Approximate Homomorphic Encryption. BMC medical genomics, 2018, 11(4): 83.2. Han K, Hong S, Cheon J H, et al. Efficient Logistic Regression on Large Encrypted Data. IACR Cryptology ePrint Archive, 2018, 2018: 662.
3. Sim J J, Chan F M, Chen S, et al. Achieving GWAS with Homomorphic Encryption. ArXiv preprint:1902.04303, 2019.
4. Kim M, Song Y, Wang S, Xia Y, Jiang X. Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation. JMIR Med Inform 2018.
Neural Networks
1. Lou Q, Feng B, Fox G C, et al. Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data. Arxiv preprint:1911.07101, 2019.2. Sirichotedumrong W, Maekawa T, Kinoshita Y, et al. Privacy-Preserving Deep Neural Networks with Pixel-based Image Encryption Considering Data Augmentation in the Encrypted Domain. Arxiv preprint:1905.01827, 2019.
3. Nandakumar K, Ratha N, Pankanti S, et al. Towards Deep Neural Network Training on Encrypted Data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2019.