A Step-by-Step Guide to Synthesizing Adversarial Examples

<p>Last week, I wrote a <a href="https://blog.openai.com/robust-adversarial-inputs/" rel="ugc">blog post</a> about how it's possible to synthesize really robust adversarial inputs for neural networks. The response was great, and I got several requests to write a tutorial on the subject because what was already out there wasn't all that accessible. <a href="http://www.anishathalye.com/2017/07/25/synthesizing-adversarial-examples/" rel="ugc">This post</a>, written in the form of an executable Jupyter notebook, is that tutorial!</p> <p>Security/ML is a fairly new area of research, but I think it's going to be pretty important in the next few years. There's even a very timely <a href="https://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack" rel="ugc">Kaggle competition</a> about this run by Google Brain. I hope that this blog post will help make this really neat area of research slightly more approachable/accessible! Also, the attacks don't require that much compute power, so you should be able to run the code from the post on your laptop.</p>

Read the full article at anishathalye.com →