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 …
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
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 …
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
Fully Homomorphic Encryption (FHE) enables offloading computation to untrusted servers
with cryptographic privacy. Despite its attractive security, FHE is not yet widely adopted due …
with cryptographic privacy. Despite its attractive security, FHE is not yet widely adopted due …
F1: A fast and programmable accelerator for fully homomorphic encryption
Fully Homomorphic Encryption (FHE) allows computing on encrypted data, enabling secure
offloading of computation to untrusted servers. Though it provides ideal security, FHE is …
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
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 …
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …
Delphi: A cryptographic inference system for neural networks
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 …
applications. However, current prediction systems compromise one party's privacy: either the …
Survey on fully homomorphic encryption, theory, and applications
Data privacy concerns are increasing significantly in the context of the Internet of Things,
cloud services, edge computing, artificial intelligence applications, and other applications …
cloud services, edge computing, artificial intelligence applications, and other applications …
Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions
Recently, the standard ResNet-20 network was successfully implemented on the fully
homomorphic encryption scheme, residue number system variant Cheon-Kim-Kim-Song …
homomorphic encryption scheme, residue number system variant Cheon-Kim-Kim-Song …
Cryptflow2: Practical 2-party secure inference
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep
Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both …
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 …
arithmetic on approximate numbers presented at Asiacrypt 2017. The attack is both …