Adversarial interference and its mitigations in privacy-preserving collaborative machine learning

D Usynin, A Ziller, M Makowski, R Braren… - Nature Machine …, 2021 - nature.com
Despite the rapid increase of data available to train machine-learning algorithms in many
domains, several applications suffer from a paucity of representative and diverse data. The …

Privacy preservation in Distributed Deep Learning: A survey on Distributed Deep Learning, privacy preservation techniques used and interesting research directions

E Antwi-Boasiako, S Zhou, Y Liao, Q Liu… - Journal of Information …, 2021 - Elsevier
Abstract Distributed or Collaborative Deep Learning, has recently gained more recognition
due to its major advantage of allowing two or more learning participants to contribute and …

{XONN}:{XNOR-based} oblivious deep neural network inference

MS Riazi, M Samragh, H Chen, K Laine… - 28th USENIX Security …, 2019 - usenix.org
Advancements in deep learning enable cloud servers to provide inference-as-a-service for
clients. In this scenario, clients send their raw data to the server to run the deep learning …

Machine learning security: Threats, countermeasures, and evaluations

M Xue, C Yuan, H Wu, Y Zhang, W Liu - IEEE Access, 2020 - ieeexplore.ieee.org
Machine learning has been pervasively used in a wide range of applications due to its
technical breakthroughs in recent years. It has demonstrated significant success in dealing …

A framework for collaborative learning in secure high-dimensional space

M Imani, Y Kim, S Riazi, J Messerly… - 2019 IEEE 12th …, 2019 - ieeexplore.ieee.org
As the amount of data generated by the Internet of the Things (IoT) devices keeps
increasing, many applications need to offload computation to the cloud. However, it often …

A Generic Cryptographic Deep-Learning Inference Platform for Remote Sensing Scenes

Q Chen, Y Wu, X Wang, ZL Jiang… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
Deep learning plays an essential role in multidisciplinary research of remote sensing. We
will encounter security problems during the data acquisition, processing, and result …

Edge-enabled distributed deep learning for 5g privacy protection

Q Sun, J Xu, X Ma, A Zhou, CH Hsu, S Wang - IEEE Network, 2021 - ieeexplore.ieee.org
Due to the limited storage and computing power, edge devices at the network edge cannot
train deep learning models locally. Traditional deep learning training requires users to …

Sealing neural network models in secure deep learning accelerators

P Zuo, Y Hua, L Liang, X **e, X Hu, Y **e - arxiv preprint arxiv …, 2020 - arxiv.org
Deep learning (DL) accelerators are increasingly deployed on edge devices to support fast
local inferences. However, they suffer from a new security problem, ie, being vulnerable to …

Refacing Defaced MRI with PixelCNN

Y **ao, W Ashbee, VD Calhoun… - 2022 International Joint …, 2022 - ieeexplore.ieee.org
Privacy protection is one of the most crucial factors when sharing MR images between
researchers. There are many defacing software programs that can blur or remove the face of …

PyHENet: A Generic Framework for Privacy-Preserving DL Inference Based on Fully Homomorphic Encryption

Q Chen, L Yao, Y Wu, X Wang, W Zhang… - … Conference on Data …, 2022 - ieeexplore.ieee.org
Deep learning inference provides inference service by service provider with model for client
with input of personal data. Due to the huge commercial value inside, on one hand, both …