Secure, privacy-preserving and federated machine learning in medical imaging

GA Kaissis, MR Makowski, D Rückert… - Nature Machine …, 2020 - nature.com
The broad application of artificial intelligence techniques in medicine is currently hindered
by limited dataset availability for algorithm training and validation, due to the absence of …

Cheetah: Lean and fast secure {Two-Party} deep neural network inference

Z Huang, W Lu, C Hong, J Ding - 31st USENIX Security Symposium …, 2022 - usenix.org
Secure two-party neural network inference (2PC-NN) can offer privacy protection for both the
client and the server and is a promising technique in the machine-learning-as-a-service …

Craterlake: a hardware accelerator for efficient unbounded computation on encrypted data

N Samardzic, A Feldmann, A Krastev… - Proceedings of the 49th …, 2022 - dl.acm.org
Fully Homomorphic Encryption (FHE) enables offloading computation to untrusted servers
with cryptographic privacy. Despite its attractive security, FHE is not yet widely adopted due …

F1: A fast and programmable accelerator for fully homomorphic encryption

N Samardzic, A Feldmann, A Krastev… - MICRO-54: 54th Annual …, 2021 - dl.acm.org
Fully Homomorphic Encryption (FHE) allows computing on encrypted data, enabling secure
offloading of computation to untrusted servers. Though it provides ideal security, FHE is …

Towards practical secure neural network inference: the journey so far and the road ahead

ZÁ Mann, C Weinert, D Chabal, JW Bos - ACM Computing Surveys, 2023 - dl.acm.org
Neural networks (NNs) have become one of the most important tools for artificial
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …

Delphi: A cryptographic inference system for neural networks

P Mishra, R Lehmkuhl, A Srinivasan, W Zheng… - Proceedings of the …, 2020 - dl.acm.org
Many companies provide neural network prediction services to users for a wide range of
applications. However, current prediction systems compromise one party's privacy: either the …

Survey on fully homomorphic encryption, theory, and applications

C Marcolla, V Sucasas, M Manzano… - Proceedings of the …, 2022 - ieeexplore.ieee.org
Data privacy concerns are increasing significantly in the context of the Internet of Things,
cloud services, edge computing, artificial intelligence applications, and other applications …

Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions

E Lee, JW Lee, J Lee, YS Kim, Y Kim… - International …, 2022 - proceedings.mlr.press
Recently, the standard ResNet-20 network was successfully implemented on the fully
homomorphic encryption scheme, residue number system variant Cheon-Kim-Kim-Song …

Cryptflow2: Practical 2-party secure inference

D Rathee, M Rathee, N Kumar, N Chandran… - Proceedings of the …, 2020 - dl.acm.org
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep
Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both …

On the security of homomorphic encryption on approximate numbers

B Li, D Micciancio - Annual International Conference on the Theory and …, 2021 - Springer
We present passive attacks against CKKS, the homomorphic encryption scheme for
arithmetic on approximate numbers presented at Asiacrypt 2017. The attack is both …