Adversarial Machine Learning Research with Florian Tramèr

This week, Anna and Tarun chat with Florian Tramèr, Assistant Professor at ETH Zurich. They discuss his earlier work on side channel attacks on privacy blockchains, as well as his academic focus on Machine Learning (ML) and adversarial research. They define some key ML terms, tease out some of the nuances of ML training and models, chat zkML and other privacy environments where ML can be trained, and look at why the security around ML will be important as these models become increasingly used in production. Here are some additional links for this episode:Episode 228: Catch-up at DevConnect AMS with Tarun, Guillermo and BrendanFlorian Tramèr’s GithubFlorian Tramèr’s Publications & PapersETH Zurich Single Secret Leader Election by Dan Boneh, Saba Eskandarian, Lucjan Hanzlik, and Nicola GrecoGasToken: A Journey Through Blockchain Resource Arbitrage by Tramèr, Daian, Breidenbach and JuelsEnter the Hydra: Towards Principled Bug Bounties and Exploit-Resistant Smart Contracts by Tramèr, Daian, Breidenbach and JuelsRonin Bridge Hack – Community Alert: Ronin Validators Compromised InstaHide: Instance-hiding Schemes for Private Distributed Learning, Huang et al. 2020.Is Private Learning Possible with Instance Encoding? OpenAI's GPT-3 modelOpenAI's GPT-2 modelOpenAI's GPT-2 modelThe Part-Time Parliament, Lamport, 1998.You Autocomplete Me: Poisoning Vulnerabilities in Neural Code CompletionZK Whiteboard Sessions – as part of ZK Hack and powered by Polygon – a new series of educational videos that will help you get onboarded into the concepts and terms that we talk about on the ZK front. ZK Jobs Board – has a fresh batch of open roles from ZK-focused projects. Find your next opportunity working in ZK!Today’s episode is sponsored by Mina...