Abstract | ||
---|---|---|
This paper explores the application of Binary Neural Networks (BNN) in oblivious inference, a service provided by a server to mistrusting clients. Using this service, a client can obtain the inference result on her data by a trained model held by the server without disclosing the data or leaning the model parameters. We make two contributions to this field. First, we devise light-weight cryptographic protocols designed specifically to exploit the unique characteristics of BNNs. Second, we present dynamic exploration of the runtime -accuracy tradeoff of BNNs in a single -shot training process. While previous works trained multiple BNNs with different computational complexities (which is cumbersome due to the slow convergence of BNNs), we train a single BNN that can perform inference under different computational budgets. Compared to CryptFlow2, the state-of-the-art in oblivious inference of non binary DNNs, our approach reaches 2x faster inference at the same accuracy. Compared to XONN, the state-of-the-art in oblivious inference of binary networks, we achieve 2x to llx faster inference while obtaining higher accuracy. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPRW53098.2021.00521 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohammad Samragh | 1 | 38 | 7.01 |
Siam U. Hussain | 2 | 69 | 6.04 |
Xinqiao Zhang | 3 | 0 | 0.34 |
Ke Huang | 4 | 0 | 0.34 |
Farinaz Koushanfar | 5 | 3055 | 268.84 |