Resources

HElayers in the News

Date	Title
2023 Apr 05	Nationwide Building Society engages IBM to assess the capability and maturity of Fully Homomorphic Encryption
2021 Jul 27	How IBM is solving the data privacy problem
2021 Apr 03	IBM bets homomorphic encryption is ready to deliver stronger data security for early adopters
2020 Jan 10	Top Brazilian Bank Pilots Privacy Encryption Quantum Computers Can’t Break

Blogs

Date	Title
2024 Jun 04	Intesa Sanpaolo and IBM secure digital transactions with fully homomorphic encryption
2024 Apr 11	IBM researchers to publish FHE challenges on the FHERMA platform
2023 Oct 16	Healthcare breach costs soar requiring new thinking for safeguarding data
2023 May 05	Building privacy-preserving federated learning to help fight financial crime
2022 Dec 16	Federated Learning meets Homomorphic Encryption
2022 Dec 08	The ultimate tool for data privacy: Fully homomorphic encryption
2022 Feb 21	IBM homomorphic encryption: A DASHing solution for healthcare data privacy
2021 Sep 06	IBM Developer Blog

Learn about tile tensors

Title	References
Advanced homomorphic encryption packing methods with applications to machine learning	[CCS 2023 Tutorial webpage, CCS 2022 Tutorial webpage]
HElayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data	[arXiv, PETs 2023]
Complex Encoded Tile Tensors: Accelerating Encrypted Analytics	[IEEE Security and Privacy]
Tutorial-HEPack4ML ‘23: Advanced HE Packing Methods with Applications to ML	[Tutorial@CCS 2023]
Demo: Rotating Wide Tensors with HElayers	[Tutorial@CCS 2023]

A 2-dimensions online tile tensors simulator is found in here.

HE-Friendly neural networks

Title	References
Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption	[arXiv, ICML 2024]
Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption	[arXiv]
HE-PEx: Efficient Machine Learning under Homomorphic Encryption using Pruning, Permutation and Expansion	[arXiv, ESORICS 2023]
Efficient Skip Connections Realization for Secure Inference on Encrypted Data	[arXiv, CSCML 2023]
A methodology for training homomorphic encryption friendly neural networks	[arXiv, SIMLA 2022]
Secure SqueezeNet inference in 4 minutes. 43rd IEEE Symposium on Security and Privacy	[s&p 2022 posters, pdf]

Other FHE papers written by IBM Research

FHE Theory

Title	References
BLEACH: Cleaning Errors in Discrete Computations over CKKS	[ePrint, JoC 2023]

Implementations optimization and security

Title	References
Secure Range-Searching Using Copy-And-Recurse	[arXiv, PETs 2024]
Privacy Preserving Feature Selection for Sparse Linear Regression	[arXiv, PETs 2024]
Efficient Privacy-Preserving Viral Strain Classification via k-mer Signatures and FHE	[ePrint, CSF 2023]
Generating One-Hot Maps under Encryption	[arXiv, CSCML 2023]
Poster: Efficient AES-GCM Decryption Under Homomorphic Encryption	[CCS 2023]
E2E near-standard and practical authenticated transciphering	[ePrint 2023]
Timing leakage analysis of non-constant-time NTT implementations with Harvey butterflies	[ePrint, CSCML 2022]
NTT software optimization using an extended Harvey butterfly	[ePrint]
Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection	[arXiv]

Privacy-Preserving Record Linkage

Title	References
Privacy-preserving record linkage using local sensitive hash and private set intersection	[arXiv, Cloud & Security 2022]

Tutorials references

Some of the tutorials that HElayers provide are based on prior-art data or on public datasets, which are listed below.

Public Datasets

Dataset	Description	Reference
Adult	Predict whether income exceeds $50K/yr based on census data. Also known as “Census Income” dataset. Number of Instances: 48842. Number of Attributes: 14	Kohavi, R., Becker, B.: Uci machine learning repository: adult dataset (1996), Link
Iris	Famous database; from Fisher, 1936. Number of Instances: 150. Number of Attributes: 4	C. L. Blake and C. J. Merz, UCI Repository of machine learning databases: iris dataset Link
ImageNet	an image database organized according to the WordNet hierarchy (currently only the nouns), in which each node of the hierarchy is depicted by hundreds and thousands of images. Image-size: 224x224x3	Link
MNIST	The MNIST database of handwritten digits, has a training set of 60,000 examples, and a test set of 10,000 examples. Image size: 28x28x1	LeCun, Yann and Cortes, Corinna. “MNIST handwritten digit database.” Link (2010)
Newsgroups	This data set consists of 20000 messages taken from 20 Usenet newsgroups.	The UCI KDD Archive Information and Computer Science University of California, Irvine , Link

Neural Network Architectures

Network name	Reference
AlexNet (Variant 1)	Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E. “Imagenet classification with deep convolutional neural networks”, Advances in neural information processing systems 25, 2012.|
CryptoNets	Gilad-Bachrach, R., Dowlin, N., Laine, K., Lauter, K., Naehrig, M. & Wernsing, J.. (2016). CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:201-210 Available here.
Lenet5	Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, “Gradient-based learning applied to document recognition,” in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998, link.
SqueezeNet	Forrest N. Iandola and Song Han and Matthew W. Moskewicz and Khalid Ashraf and William J. Dally and Kurt Keutzer, “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size”, 2016, link.
SqueezeNet CHET	Roshan Dathathri, Olli Saarikivi, Hao Chen, Kim Laine, Kristin Lauter, Saeed Maleki, Madanlal Musuvathi, and Todd Mytkowicz. 2019. CHET: an optimizing compiler for fully-homomorphic neural-network inferencing. In Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2019). Association for Computing Machinery, New York, NY, USA, 142–156, link.
ResNet	Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778 link.

Credit card fraud detection using NN inference

• Andrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015

• Dal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon

• Dal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE

• Dal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)

• Carcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-Aël; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier

• Carcillo, Fabrizio; Le Borgne, Yann-Aël; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing

• Bertrand Lebichot, Yann-Aël Le Borgne, Liyun He, Frederic Oblé, Gianluca Bontempi Deep-Learning Domain Adaptation Techniques for Credit Cards Fraud Detection, INNSBDDL 2019: Recent Advances in Big Data and Deep Learning, pp 78-88, 2019

• Fabrizio Carcillo, Yann-Aël Le Borgne, Olivier Caelen, Frederic Oblé, Gianluca Bontempi Combining Unsupervised and Supervised Learning in Credit Card Fraud Detection Information Sciences, 2019

• Yann-Aël Le Borgne, Gianluca Bontempi Machine Learning for Credit Card Fraud Detection - Practical Handbook

Heart disease detection using NN inference

• https://archive.ics.uci.edu/ml/datasets/Heart+Disease

• Detrano, R., Janosi, A., Steinbrunn, W., Pfisterer, M., Schmid, J., Sandhu, S., Guppy, K., Lee, S., & Froelicher, V. (1989). International application of a new probability algorithm for the diagnosis of coronary artery disease. American Journal of Cardiology, 64,304–310.

• David W. Aha & Dennis Kibler. “Instance-based prediction of heart-disease presence with the Cleveland database.”

• Gennari, J.H., Langley, P, & Fisher, D. (1989). Models of incremental concept formation. Artificial Intelligence, 40, 11–61.

Completely Random Forest

• Aslett, Louis JM, Pedro M. Esperança, and Chris C. Holmes. “Encrypted statistical machine learning: new privacy preserving methods.” arXiv preprint arXiv:1508.06845 (2015).