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.

Bridging machine learning and cryptography in defence against adversarial attacks

5 Sep 20182 code implementations

The majority of the proposed existing adversarial attacks are based on the differentiability of the DNN cost function. Defence strategies are mostly based on machine learning and signal processing principles that either try to detect-reject or filter out the adversarial perturbations and completely neglect the classical cryptographic component in the defence.

Unsupervised Steganalysis Based on Artificial Training Sets

2 Mar 20171 code implementation

In this paper, an unsupervised steganalysis method that combines artificial training setsand supervised classification is proposed.

SteganoGAN: High Capacity Image Steganography with GANs

12 Jan 20191 code implementation

Image steganography is a procedure for hiding messages inside pictures.

IMAGE STEGANOGRAPHY

Balanced Crossover Operators in Genetic Algorithms

23 Apr 20191 code implementation

Furthermore, in two out of three crossovers, the "left-to-right" version performs better than the "shuffled" version.

COMBINATORIAL OPTIMIZATION

Visual cryptography in single-pixel imaging

12 Nov 2019no code implementations

The secret image can be recovered when identical illumination patterns are projected onto multiple visual key images and a single detector is used to record the total light intensities.

Using Echo State Networks for Cryptography

4 Apr 2017no code implementations

The key idea is to assume that Alice and Bob share a copy of an echo state network.

A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component

21 Aug 2019no code implementations

In this paper, we propose a novel privacy-preserving deep learning model and a secure training/inference scheme to protect the input, the output, and the model in the application of the neural network.

PRIVACY PRESERVING DEEP LEARNING

A characterisation of S-box fitness landscapes in cryptography

13 Feb 2019no code implementations

Substitution Boxes (S-boxes) are nonlinear objects often used in the design of cryptographic algorithms.

PD-ML-Lite: Private Distributed Machine Learning from Lighweight Cryptography

23 Jan 2019no code implementations

We apply our methodology to two major ML algorithms, namely non-negative matrix factorization (NMF) and singular value decomposition (SVD).

RECOMMENDATION SYSTEMS REGRESSION