A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions

X Yin, Y Zhu, J Hu - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
The past four years have witnessed the rapid development of federated learning (FL).
However, new privacy concerns have also emerged during the aggregation of the …

[HTML][HTML] Privacy-preserving neural networks with homomorphic encryption: C hallenges and opportunities

B Pulido-Gaytan, A Tchernykh… - Peer-to-Peer Networking …, 2021 - Springer
Classical machine learning modeling demands considerable computing power for internal
calculations and training with big data in a reasonable amount of time. In recent years …

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 …

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 …

Bts: An accelerator for bootstrappable fully homomorphic encryption

S Kim, J Kim, MJ Kim, W Jung, J Kim, M Rhu… - Proceedings of the 49th …, 2022 - dl.acm.org
Homomorphic encryption (HE) enables the secure offloading of computations to the cloud by
providing computation on encrypted data (ciphertexts). HE is based on noisy encryption …

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 …

A study of face obfuscation in imagenet

K Yang, JH Yau, L Fei-Fei, J Deng… - International …, 2022 - proceedings.mlr.press
Face obfuscation (blurring, mosaicing, etc.) has been shown to be effective for privacy
protection; nevertheless, object recognition research typically assumes access to complete …