Today we’re joined by Nicholas Carlini, a research scientist at Google Brain. Nicholas works at the intersection of machine learning and computer security, and his recent paper “Extracting Training Data from LLMs” has generated quite a buzz within the ML community. In our conversation, we discuss the current state of adversarial machine learning research, the dynamic of dealing with privacy issues in black box vs accessible models, what privacy attacks in vision models like diffusion models look like, and the scale of “memorization” within these models. We also explore Nicholas’ work on data poisoning, which looks to understand what happens if a bad actor can take control of a small fraction of the data that an ML model is trained on.
The complete show notes for this episode can be found at twimlai.com/go/618.
Learning to Ponder: Memory in Deep Neural Networks with Andrea Banino - #528
Advancing Deep Reinforcement Learning with NetHack, w/ Tim Rocktäschel - #527
Building Technical Communities at Stack Overflow with Prashanth Chandrasekar - #526
Deep Learning is Eating 5G. Here’s How, w/ Joseph Soriaga - #525
Modeling Human Cognition with RNNs and Curriculum Learning, w/ Kanaka Rajan - #524
Do You Dare Run Your ML Experiments in Production? with Ville Tuulos - #523
Delivering Neural Speech Services at Scale with Li Jiang - #522
AI’s Legal and Ethical Implications with Sandra Wachter - #521
Compositional ML and the Future of Software Development with Dillon Erb - #520
Generating SQL Database Queries from Natural Language with Yanshuai Cao - #519
Social Commonsense Reasoning with Yejin Choi - #518
Deep Reinforcement Learning for Game Testing at EA with Konrad Tollmar - #517
Exploring AI 2041 with Kai-Fu Lee - #516
Advancing Robotic Brains and Bodies with Daniela Rus - #515
Neural Synthesis of Binaural Speech From Mono Audio with Alexander Richard - #514
Using Brain Imaging to Improve Neural Networks with Alona Fyshe - #513
Adaptivity in Machine Learning with Samory Kpotufe - #512
A Social Scientist’s Perspective on AI with Eric Rice - #511
Applications of Variational Autoencoders and Bayesian Optimization with José Miguel Hernández Lobato - #510
Codex, OpenAI’s Automated Code Generation API with Greg Brockman - #509
Create your
podcast in
minutes
It is Free
20/20
The Dropout
Ten Percent Happier with Dan Harris
World News Tonight with David Muir
NEJM This Week