A generic framework for privacy preserving deep learning

9 Nov 20183 code implementations

We detail a new framework for privacy preserving deep learning and discuss its assets.


Private Machine Learning in TensorFlow using Secure Computation

18 Oct 20182 code implementations

We present a framework for experimenting with secure multi-party computation directly in TensorFlow.

Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learning

8 Sep 20172 code implementations

Our proposed scheme, called "Deep Packet," can handle both \emph{traffic characterization} in which the network traffic is categorized into major classes (\eg, FTP and P2P) and application identification in which end-user applications (\eg, BitTorrent and Skype) identification is desired.

TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service

ICML 2018 1 code implementation

The main drawback of using fully homomorphic encryption is the amount of time required to evaluate large machine learning models on encrypted data.

Partially Encrypted Machine Learning using Functional Encryption

24 May 20191 code implementation

Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation.

Low Latency Privacy Preserving Inference

ICLR 2019 1 code implementation

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity.


Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)

13 Oct 20174 code implementations

This article describes the design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge.


Learning to Protect Communications with Adversarial Neural Cryptography

21 Oct 20163 code implementations

We ask whether neural networks can learn to use secret keys to protect information from other neural networks.

An IoT Endpoint System-on-Chip for Secure and Energy-Efficient Near-Sensor Analytics

18 Dec 20163 code implementations

Near-sensor data analytics is a promising direction for IoT endpoints, as it minimizes energy spent on communication and reduces network load - but it also poses security concerns, as valuable data is stored or sent over the network at various stages of the analytics pipeline.


SHE: A Fast and Accurate Deep Neural Network for Encrypted Data

NeurIPS 2019 1 code implementation

Since the LTFHE ReLU activations, max poolings, shifts and accumulations have small multiplicative depth overhead, SHE can implement much deeper network architectures with more convolutional and activation layers.