Today we’re joined by Aleksander Madry, Faculty in the MIT EECS Department, to discuss his paper “Adversarial Examples Are Not Bugs, They Are Features.” In our conversation, we talk through what we expect these systems to do, vs what they’re actually doing, if we’re able to characterize these patterns, and what makes them compelling, and if the insights from the paper will help inform opinions on either side of the deep learning debate.

Adversarial Examples Are Not Bugs, They Are Features with Aleksander Madry - #369

Machine learning and artificial intelligence are dramatically changing the way businesses operate and people live. The TWIML AI Podcast brings the top minds and ideas from the world of ML and AI to a broad and influential community of ML/AI researchers, data scientists, engineers and tech-savvy business and IT leaders. Hosted by Sam Charrington, a sought after industry analyst, speaker, commentator and thought leader. Technologies covered include machine learning, artificial intelligence, deep learning, natural language processing, neural networks, analytics, computer science, data science and more.

Technology

Tech News

Podcasting

Gadgets

Software How-To

News

Science

Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models.

The complete show notes for this episode can be found at twimlai.com/go/679.

Localizing and Editing Knowledge in LLMs with Peter Hase - #679

Today we're joined by Jonas Geiping, a research group leader at the ELLIS Institute, to explore his paper: "Coercing LLMs to Do and Reveal (Almost) Anything". Jonas explains how neural networks can be exploited, highlighting the risk of deploying LLM agents that interact with the real world. We discuss the role of open models in enabling security research, the challenges of optimizing over certain constraints, and the ongoing difficulties in achieving robustness in neural networks. Finally, we delve into the future of AI security, and the need for a better approach to mitigate the risks posed by optimized adversarial attacks.

The complete show notes for this episode can be found at twimlai.com/go/678.

Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678

Today we’re joined by Mido Assran, a research scientist at Meta’s Fundamental AI Research (FAIR). In this conversation, we discuss V-JEPA, a new model being billed as “the next step in Yann LeCun's vision” for true artificial reasoning. V-JEPA, the video version of Meta’s Joint Embedding Predictive Architecture, aims to bridge the gap between human and machine intelligence by training models to learn abstract concepts in a more efficient predictive manner than generative models. V-JEPA uses a novel self-supervised training approach that allows it to learn from unlabeled video data without being distracted by pixel-level detail. Mido walks us through the process of developing the architecture and explains why it has the potential to revolutionize AI.

The complete show notes for this episode can be found at twimlai.com/go/677.

V-JEPA, AI Reasoning from a Non-Generative Architecture with Mido Assran - #677

Today we’re joined by Sherry Yang, senior research scientist at Google DeepMind and a PhD student at UC Berkeley. In this interview, we discuss her new paper, "Video as the New Language for Real-World Decision Making,” which explores how generative video models can play a role similar to language models as a way to solve tasks in the real world. Sherry draws the analogy between natural language as a unified representation of information and text prediction as a common task interface and demonstrates how video as a medium and generative video as a task exhibit similar properties. This formulation enables video generation models to play a variety of real-world roles as planners, agents, compute engines, and environment simulators. Finally, we explore UniSim, an interactive demo of Sherry's work and a preview of her vision for interacting with AI-generated environments.

The complete show notes for this episode can be found at twimlai.com/go/676.

Video as a Universal Interface for AI Reasoning with Sherry Yang - #676

Today we’re joined by Sayash Kapoor, a Ph.D. student in the Department of Computer Science at Princeton University. Sayash walks us through his paper: "On the Societal Impact of Open Foundation Models.” We dig into the controversy around AI safety, the risks and benefits of releasing open model weights, and how we can establish common ground for assessing the threats posed by AI. We discuss the application of the framework presented in the paper to specific risks, such as the biosecurity risk of open LLMs, as well as the growing problem of "Non Consensual Intimate Imagery" using open diffusion models.

The complete show notes for this episode can be found at twimlai.com/go/675.

Adversarial Examples Are Not Bugs, They Are Features with Aleksander Madry - #369

Download our free app to listen on your phone