87 citations · 809 across the 93 of their papers we have counts for
5 papers · 1 filter
ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition
Song Bian, Tianchen Wang, Masayuki Hiromoto +2
In this work, we propose ENSEI, a secure inference (SI) framework based on the frequency-domain secure convolution (FDSC) protocol for the efficient execution of privacy-preserving…
NASS: Optimizing Secure Inference via Neural Architecture Search
Song Bian, Weiwen Jiang, Qing Lu +2
Due to increasing privacy concerns, neural network (NN) based secure inference (SI) schemes that simultaneously hide the client inputs and server models attract major research inte…
Privacy-Aware Cost-Effective Scheduling Considering Non-Schedulable Appliances in Smart Home
Boyang Li, Jie Wu, Yiyu Shi
A Smart Home provides integrating and electronic information services to help residential users manage their energy usage and bill cost but also exposes users to significant privac…
Real-Time Adversarial Attacks
Yuan Gong, Boyang Li, Christian Poellabauer +1
In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on…
Energy-recycling Blockchain with Proof-of-Deep-Learning
Changhao Chenli, Boyang Li, Yiyu Shi +1
An enormous amount of energy is wasted in Proofof-Work (PoW) mechanisms adopted by popular blockchain applications (e.g., PoW-based cryptocurrencies), because miners must conduct a…