搜索结果: 1-10 共查到“军事学 inference”相关记录10条 . 查询时间(0.031 秒)
CrypTFlow: Secure TensorFlow Inference
secure multi-party computation implementation TensorFlow
2019/9/19
We present CrypTFlow, a first of its kind system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build three compone...
nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
Privacy-Preserving Machine Learning Deep Learning Graph Compilers
2019/8/21
In previous work, Boemer et al. introduced nGraph-HE, an extension to the Intel nGraph deep learning (DL) compiler, that en- ables data scientists to deploy models with popular frameworks such as Tens...
Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference
multi-key homomorphic encryption packed ciphertext ring learning with errors
2019/5/21
Homomorphic Encryption (HE) is a cryptosystem which supports computation on encrypted data. López-Alt et al. (STOC 2012) proposed a generalized notion of HE, called Multi-Key Homomorphic Encryption (M...
XONN: XNOR-based Oblivious Deep Neural Network Inference
Privacy-Preserving Machine Learning Deep Learning Oblivious Inference
2019/2/25
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 ba...
A Systematic Study of the Impact of Graphical Models on Inference-based Attacks on AES
Belief Propagation Factor Graphs AES
2018/7/16
We define a novel metric to capture the importance of variable nodes in factor graphs, we propose two improvements to the sum-product algorithm for the specific use case in side channel analysis, and ...
GAZELLE: A Low Latency Framework for Secure Neural Network Inference
homomorphic encryption two-party secure computation convolutional neural networks
2018/1/19
The growing popularity of cloud-based machine learning raises a natural question about the privacy guarantees that can be provided in such a setting. Our work tackles this problem in the context where...
The Tao of Inference in Privacy-Protected Databases
inference attacks encrypted databases privacy
2017/11/13
To protect database confidentiality even in the face of full compromise while supporting standard functionality, recent academic proposals and commercial products rely on a mix of encryption schemes. ...
Inference and Record-Injection Attacks on Searchable Encrypted Relational Databases
searchable symmetric encryption inference attacks complexity theory
2017/2/20
We point out the risks of providing security to relational databases via searchable encryption schemes by mounting a novel inference attack exploiting the structure of relational databases together wi...
Trading-Off Type-Inference Memory Complexity Against Communication
Trading-Off Type-Inference Memory Complexity Java applets
2009/4/9
While bringing considerable °exibility and extending the
horizons of mobile computing, mobile code raises major security issues.
Hence, mobile code, such as Java applets, needs to be analyzed before...
Private Inference Control
Private information retrieval oblivious transfer inference control
2009/3/27
Access control can be used to ensure that database queries pertaining to sensitive information are not answered. This is not enough to prevent users from learning sensitive information though, because...