Episode Synopsis "5. Generative-Adversarial Neural Networks and Voiceprint Systems with Zach Trefler"

Brendon and Anish interview Zach Trefler, a student at the University of Toronto, about his research on designing neural networks to create adversarial examples to defeat, and then improve the security of, a voiceprinting system. We discuss how generative-adversarial networks are applied and how they can be applied to generate adversarial examples, in order to trick a security system into classifying the examples as a completely different user, and then how this can be used to develop a more secure system. Please send comments to .

Listen "5. Generative-Adversarial Neural Networks and Voiceprint Systems with Zach Trefler"

More episodes of the podcast Shattered Gradients

• 1. Hello World, and Vision for Autonomous Vehicles
• 2. Real-World Ethics in Deep Learning, with Jacky Zhao
• 3. David Holz on Building a Career in Silicon Valley and the Future of Deep Learning (Live at ISEF)
• 4. Deep Learning in Embedded Electronics for Short-Term Storm Forecasting with Max von Wolff
• 5. Generative-Adversarial Neural Networks and Voiceprint Systems with Zach Trefler
• 6. Genetic Algorithms with Filip Kučerak
• 7. Seeing Through Walls with Kevin Meng
• 8. Everything Under the Sun with Krithik Ramesh