Defending Against Adversarial Attacks

Algorithms can produce impressive results while still leaving important questions unanswered. Our host Kyle interviews Gokula Krishnan from ETH Zurich, about his recent contributions to defenses against adversarial attacks. The discussion centers around his latest paper, titled “Defending Against Adversarial Attacks by Leveraging an Entire GAN,” and his proposed algorithm, aptly named ‘Cowboy.’

Guest

Gokula Krishnan: Currently a Masters student in CS at ETH focusing on Machine Learning and Distributed Systems. I did my Bachelors from BITS Pilani, India and graduated with distinction. I have worked on a wide range of topics including IoT, Intelligent Vehicle Systems, Computer Networks, as well as Machine Learning and AI. I have interned at Georgia Tech and Indian Space Research Organization working on Machine Learning Projects.