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 Transformer Programs with Dan Friedman - #667
AI Trends 2024: Machine Learning & Deep Learning with Thomas Dietterich - #666
AI Trends 2024: Computer Vision with Naila Murray - #665
Are Vector DBs the Future Data Platform for AI? with Ed Anuff - #664
Quantizing Transformers by Helping Attention Heads Do Nothing with Markus Nagel - #663
Responsible AI in the Generative Era with Michael Kearns - #662
Edutainment for AI and AWS PartyRock with Mike Miller - #661
Data, Systems and ML for Visual Understanding with Cody Coleman - #660
Patterns and Middleware for LLM Applications with Kyle Roche - #659
AI Access and Inclusivity as a Technical Challenge with Prem Natarajan - #658
Building LLM-Based Applications with Azure OpenAI with Jay Emery - #657
Visual Generative AI Ecosystem Challenges with Richard Zhang - #656
Deploying Edge and Embedded AI Systems with Heather Gorr - #655
AI Sentience, Agency and Catastrophic Risk with Yoshua Bengio - #654
Delivering AI Systems in Highly Regulated Environments with Miriam Friedel - #653
Mental Models for Advanced ChatGPT Prompting with Riley Goodside - #652
Multilingual LLMs and the Values Divide in AI with Sara Hooker - #651
Scaling Multi-Modal Generative AI with Luke Zettlemoyer - #650
Pushing Back on AI Hype with Alex Hanna - #649
Personalization for Text-to-Image Generative AI with Nataniel Ruiz - #648
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