搜索结果: 1-10 共查到“军事学 neural networks”相关记录10条 . 查询时间(0.081 秒)
Interpretable Encrypted Searchable Neural Networks
Searchable Encryption Searchable Neural Networks Probabilistic Learning
font style='font-size:12px;'>
2019/8/19
In cloud security, traditional searchable encryption (SE) requires high computation and communication overhead for dynamic search and update. The clever combination of machine learning (ML) and SE may...
Garbled Neural Networks are Practical
garbled circuits neural networks
font style='font-size:12px;'>
2019/4/3
We show that garbled circuits are a practical choice for secure evaluation of neural network classifiers. At the protocol level, we start with the garbling scheme of Ball, Malkin & Rosulek (ACM CCS 20...
Secure Evaluation of Quantized Neural Networks
Machine Learning Multi-Party Computation Quantization
font style='font-size:12px;'>
2019/2/27
Machine Learning models, and specially convolutional neural networks (CNNs), are at the heart of many day-to-day applications like image classification and speech recognition. The need for evaluating ...
Fast Secure Comparison for Medium-Sized Integers and Its Application in Binarized Neural Networks
multiparty computation secret sharing secure comparison
font style='font-size:12px;'>
2019/1/2
In 1994, Feige, Kilian, and Naor proposed a simple protocol for secure 33-way comparison of integers aa and bb from the range [0,2][0,2]. Their observation is that for p=7p=7, the Legendre symbol (x|p...
Make Some Noise: Unleashing the Power of Convolutional Neural Networks for Profiled Side-channel Analysis
Side-channel analysis Convolutional Neural Networks Machine learning
font style='font-size:12px;'>
2018/11/2
Profiled side-channel attacks based on deep learning, and more precisely Convolutional Neural Networks, is a paradigm showing significant potential. The results, although scarce for now, suggest that ...
Secure Outsourced Matrix Computation and Application to Neural Networks
Homomorphic encryption matrix computation machine learning
font style='font-size:12px;'>
2018/11/2
Homomorphic Encryption (HE) is a powerful cryptographic primitive to address privacy and security issues in outsourcing computation on sensitive data to an untrusted computation environment. Comparing...
DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networks
CNNs WRNs
font style='font-size:12px;'>
2018/4/10
This paper proposes DeepMarks, a novel end-to-end framework for systematic fingerprinting in the context of Deep Learning (DL). Remarkable progress has been made in the area of deep learning. Sharing ...
Fast Homomorphic Evaluation of Deep Discretized Neural Networks
Fully Homomorphic Encryption Neural Networks Bootstrapping
font style='font-size:12px;'>
2017/11/21
The rise of machine learning -- and most particularly the one of deep neural networks -- multiplies scenarios where one faces a privacy dilemma: either sensitive user data must be revealed to the enti...
Embedded Proofs for Verifiable Neural Networks
verifiable computation proof composition neural networks
font style='font-size:12px;'>
2017/10/30
The increasing use of machine learning algorithms to deal with large amount of data and the expertise required by these algorithms lead users to outsource machine learning services. This raises a trus...
Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures -- Profiling Attacks without Pre-Processing --
side channel attacks machine learning deep learning
font style='font-size:12px;'>
2017/8/10
In the context of the security evaluation of cryptographic implementations, profiling attacks (aka Template Attacks) play a fundamental role. Nowadays the most popular Template Attack strategy consist...