Abstract | ||
---|---|---|
Complex machine learning (ML) inference algorithms like recurrent neural networks (RNNs) use standard functions from math libraries like exponentiation, sigmoid, tanh, and reciprocal of square root. Although prior work on secure 2-party inference provides specialized protocols for convolutional neural networks (CNNs), existing secure implementations of these math operators rely on generic 2-party ... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/SP40001.2021.00086 | 2021 IEEE Symposium on Security and Privacy (SP) |
Keywords | DocType | ISBN |
privacy-preserving machine learning,secure two-party computation,recurrent neural networks,math functions,mixed-bitwidths,secure inference | Conference | 978-1-7281-8934-5 |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Deevashwer Rathee | 1 | 1 | 2.37 |
Mayank Rathee | 2 | 4 | 1.44 |
Rahul Kranti Kiran Goli | 3 | 1 | 0.35 |
Divya Gupta 0001 | 4 | 95 | 7.44 |
Rahul Sharma | 5 | 366 | 16.39 |
Nishanth Chandran | 6 | 375 | 21.86 |
Aseem Rastogi | 7 | 133 | 14.49 |