Cleverhans – Lib python para prevenção de ataques de ruídos nos modelos

É um tema bem recente o ataque em sensores e por consequência em modelos de Machine Learning (isso será abordado em algum momento do futuro por aqui, mas esse artigo mostra bem o potencial danoso disso).

O Cleverhans é uma lib em Python que insere de maneira artificial um pouco de ruído/distúrbio na rede como forma de treino para esse tipo de ataque.

This repository contains the source code for cleverhans, a Python library to benchmark machine learning systems’ vulnerability to adversarial examples. You can learn more about such vulnerabilities on the accompanying blog.

The cleverhans library is under continual development, always welcoming contributions of the latest attacks and defenses. In particular, we always welcome help towards resolving the issues currently open.

About the name

The name cleverhans is a reference to a presentation by Bob Sturm titled “Clever Hans, Clever Algorithms: Are Your Machine Learnings Learning What You Think?” and the corresponding publication, “A Simple Method to Determine if a Music Information Retrieval System is a ‘Horse’.” Clever Hans was a horse that appeared to have learned to answer arithmetic questions, but had in fact only learned to read social cues that enabled him to give the correct answer. In controlled settings where he could not see people’s faces or receive other feedback, he was unable to answer the same questions. The story of Clever Hans is a metaphor for machine learning systems that may achieve very high accuracy on a test set drawn from the same distribution as the training data, but that do not actually understand the underlying task and perform poorly on other inputs.

Anúncios
Cleverhans – Lib python para prevenção de ataques de ruídos nos modelos

Softmax GAN

Abstract: Softmax GAN is a novel variant of Generative Adversarial Network (GAN). The key idea of Softmax GAN is to replace the classification loss in the original GAN with a softmax cross-entropy loss in the sample space of one single batch. In the adversarial learning of N real training samples and M generated samples, the target of discriminator training is to distribute all the probability mass to the real samples, each with probability 1M, and distribute zero probability to generated data. In the generator training phase, the target is to assign equal probability to all data points in the batch, each with probability 1M+N. While the original GAN is closely related to Noise Contrastive Estimation (NCE), we show that Softmax GAN is the Importance Sampling version of GAN. We futher demonstrate with experiments that this simple change stabilizes GAN training.

Softmax GAN