| Paper ID | IFS-6.6 |
| Paper Title |
CRYPTO-ORIENTED NEURAL ARCHITECTURE DESIGN |
| Authors |
Avital Shafran, Gil Segev, Shmuel Peleg, Yedid Hoshen, The Hebrew University of Jerusalem, Israel |
| Session | IFS-6: Anonymization, Security and Privacy |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation |
Poster
|
| Topic |
Information Forensics and Security: [ADP] Anonymization And Data Privacy |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Sending private data to Neural Network applications raises many privacy concerns. The cryptography community developed a variety of secure computation methods to address such privacy issues. As generic techniques for secure computation are typically prohibitively expensive, efforts focus on optimizing these cryptographic tools. Differently, we propose to optimize the design of crypto-oriented neural architectures, introducing a novel Partial Activation layer. The proposed layer is much faster for secure computation as it contains fewer non linear computations. Evaluating our method on three state-of-the-art architectures (SqueezeNet, ShuffleNetV2, and MobileNetV2) demonstrate significant improvement to the efficiency of secure inference on common evaluation metrics. |
