When I first was introduced to the idea of adversarial learning for security purposes by Clarence Chio's 2016 DEF CON talk and his related open-source library deep-pwning, I immediately started wondering about applications of the field to both make robust and well-tested models, but also as a preventative measure against predatory machine learning practices in the field. After reading more literature and utilizing several other open-source libraries, I realized most examples and research focused around malicious uses, such as sending spam or malware without detection, or crashing self-driving cars. Although I find this research interesting, I wanted to determine if adversarial learning could be used for "good".1 In case you haven't been following the explosion of adversarial learning in neural network research, papers and conferences, let's take a whirlwind tour of some concepts to get on the same page and provide further reading if you open up arXiv for fun on the weekend. Similarly to how we use the loss function to train our network, researchers found we can use this same method to find weak links in our network and adversarial examples that exploit them.

Your browser can't play this video file. Please download the file below and use a desktop player e.g. In the past decade, machine learning researchers and theorists have created deep learning architectures which seem to learn complex topics with little intervention. Newer research in adversarial learning questions just how much "learning" these networks are doing. Several theories have arisen regarding neural network "blind spots" which can be exploited to fool the network.