Towards Adversarial Robustness via Feature Matching

Adversarial Feature Matching for Text Generation

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (realvalued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We employ a long shortterm memory network as generator, and a convolutional network ...

Towards Proving the Adversarial Robustness of Deep Neural Networks

Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficult, but there has been some success in using deep neural networks generated using machine-learning. However, deep neural networks are opaque to human engineers, rendering their correctness very difficult to prove manua...

Improving Generative Adversarial Networks with Denoising Feature Matching

We propose an augmented training procedure for generative adversarial networks designed to address shortcomings of the original by directing the generator towards probable configurations of abstract discriminator features. We estimate and track the distribution of these features, as computed from data, with a denoising auto-encoder, and use it to propose high-level targets for the generator. We...

Deep Adversarial Robustness

Deep learning has recently contributed to learning state-of-the-art representations in service of various image recognition tasks. Deep learning uses cascades of many layers of nonlinear processing units for feature extraction and transformation. Recently, researchers have shown that deep learning architectures are particularly vulnerable to adversarial examples, inputs to machine learning mode...

Towards a Standardised Testsuite to Assess Fingerprint Matching Robustness: The StirMark Toolkit - Cross-Feature Type Comparisons