Adversarial-Playground: A Visualization Suite for Adversarial Sample Generation
This provides a tool for machine learning practitioners and users to understand model vulnerabilities, but it is incremental as it builds on existing methods.
The authors tackled the problem of making adversarial machine learning more accessible by developing Adversarial-Playground, a web-based visualization tool that demonstrates common adversarial methods against deep neural networks, resulting in a faster variant of a state-of-the-art approach with comparable evasion rates.
With growing interest in adversarial machine learning, it is important for machine learning practitioners and users to understand how their models may be attacked. We propose a web-based visualization tool, Adversarial-Playground, to demonstrate the efficacy of common adversarial methods against a deep neural network (DNN) model, built on top of the TensorFlow library. Adversarial-Playground provides users an efficient and effective experience in exploring techniques generating adversarial examples, which are inputs crafted by an adversary to fool a machine learning system. To enable Adversarial-Playground to generate quick and accurate responses for users, we use two primary tactics: (1) We propose a faster variant of the state-of-the-art Jacobian saliency map approach that maintains a comparable evasion rate. (2) Our visualization does not transmit the generated adversarial images to the client, but rather only the matrix describing the sample and the vector representing classification likelihoods. The source code along with the data from all of our experiments are available at \url{https://github.com/QData/AdversarialDNN-Playground}.