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.
Ensuring LLM Safety for Production Applications with Shreya Rajpal - #647
What’s Next in LLM Reasoning? with Roland Memisevic - #646
Is ChatGPT Getting Worse? with James Zou - #645
Why Deep Networks and Brains Learn Similar Features with Sophia Sanborn - #644
Inverse Reinforcement Learning Without RL with Gokul Swamy - #643
Explainable AI for Biology and Medicine with Su-In Lee - #642
Transformers On Large-Scale Graphs with Bayan Bruss - #641
The Enterprise LLM Landscape with Atul Deo - #640
BloombergGPT - an LLM for Finance with David Rosenberg - #639
Are LLMs Good at Causal Reasoning? with Robert Osazuwa Ness - #638
Privacy vs Fairness in Computer Vision with Alice Xiang - #637
Unifying Vision and Language Models with Mohit Bansal - #636
Data Augmentation and Optimized Architectures for Computer Vision with Fatih Porikli - #635
Mojo: A Supercharged Python for AI with Chris Lattner - #634
Stable Diffusion and LLMs at the Edge with Jilei Hou - #633
Modeling Human Behavior with Generative Agents with Joon Sung Park - #632
Towards Improved Transfer Learning with Hugo Larochelle - #631
Language Modeling With State Space Models with Dan Fu - #630
Building Maps and Spatial Awareness in Blind AI Agents with Dhruv Batra - #629
AI Agents and Data Integration with GPT and LLaMa with Jerry Liu - #628
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