WebFeb 19, 2024 · 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 model and send back the results. One standing challenge in this setting is to ensure the privacy of the clients' sensitive data. Oblivious inference is the task of … Web[9] Rathee, Deevashwer, et al. "CrypTFlow2: Practical 2-party secure inference." Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security. 2024. [10] Chandran, Nishanth, et al. "EzPC: programmable and efficient secure two-party computation for machine learning."

Divya Gupta at Microsoft Research

WebMay 6, 2024 · We conduct ImageNet-scale inference on practical ResNet50 model and it costs less than 5.5 minutes and 10.117 Gb of communication, which only brings additional 29% runtime and has 2.643$\times ... WebMay 10, 2024 · We build on top of our novel protocols to build SIRNN, a library for end-to-end secure 2-party DNN inference, that provides the first secure implementations of an RNN operating on time series sensor data, an RNN operating on speech data, and a state-of-the-art ML architecture that combines CNNs and RNNs for identifying all heads … reachcliff cave

CrypTFlow2: Practical 2-Party Secure Inference DeepAI

WebCrypTFlow2: Practical 2-party secure inference. ... SIRNN: A math library for secure inference of RNNs. D Rathee, M Rathee, RKK Goli, D Gupta, R Sharma, N Chandran, ... IEEE S&P, 2024. 7: 2024: SecFloat: Accurate Floating-Point meets Secure 2 … WebMay 11, 2024 · We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation. WebAt the core of CrypTFlow2, we have new 2PC protocols for secure comparison and division, designed carefully to balance round and communication complexity for secure … reachcliff cave how to open secret door