logo
episode-header-image
Feb 2023
43m 11s

Privacy and Security for Stable Diffusio...

Sam Charrington
About this episode
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, th ... Show More
Up next
Today
From Voice Agents to AI Avatars with Alexander Smola - #777
Voice AI has gotten remarkably good, but natural conversation remains a high bar. Small delays, awkward interruptions, or the wrong tone can quickly break the illusion—and adding vision and visual presence only raises the stakes. In this episode, Alex Smola, co-founder and CEO of ... Show More
1h 4m
Sep 9
Do AI Tokenomics Matter More Than Model Benchmarks? with Chris Potts - #776
As reasoning models consume more tokens and AI systems become more expensive to run, understanding what those tokens actually buy is becoming increasingly important. In this episode, Stanford professor and Big Spin co-founder Chris Potts joins us to discuss AI tokenomics and his ... Show More
59m 29s
Sep 1
World Models and the Future of Spatial AI with Justin Johnson - #775
In this episode, Justin Johnson, co-founder of World Labs, joins us to discuss world models and the emerging field of spatial AI. We explore why many researchers see capabilities beyond language as an important frontier for AI, and what it means to build models that can understan ... Show More
1h 6m
Recommended Episodes
Mar 2024
LLM Security and Privacy
<p>Sean Falconer (@seanfalconer, Head of Dev Relations @SkyflowAPI, Host @software_daily) talks about security and privacy of LLMs and how to prevent PII (personally identifiable information) from leaking out</p><p><b>SHOW: 807<br/><br/>CLOUD NEWS OF THE WEEK - </b><a href='http: ... Show More
26m 9s
Jun 2023
Managing machine learning risks. [Research Saturday]
Our guest, Johannes Ullrich from SANS Institute, joins Dave to discuss their research on "Machine Learning Risks: Attacks Against Apache NiFi." Using their honeypot network, researchers were able to collect some interesting data about a threat actor who is currently going after e ... Show More
18m 34s
Dec 2017
Mercedes Benz Machine Learning Research
<p class="p1"><span class="s1">This episode features an interview with Rigel Smiroldo recorded at NIPS 2017 in Long Beach California.<span class="Apple-converted-space"> </span> We discuss data privacy, machine learning use cases, model deployment, and end-to-end machine learning ... Show More
27m 5s
Sep 2023
LLMs for Evil
We are joined by Maximilian Mozes, a PhD student at the University College, London. His PhD research focuses on Natural Language Processing (NLP), particularly the intersection of adversarial machine learning and NLP. He joins us to discuss his latest research, Use of LLMs for Il ... Show More
26m 13s
Sep 2024
20VC: OpenAI's Newest Board Member, Zico Colter on The Biggest Bottlenecks to the Performance of Foundation Models | The Biggest Questions and Concerns in AI Safety | How to Regulate an AI-Centric World
<p><!-- wp:paragraph --></p> <p>Zico Colter is a Professor and the Director of the Machine Learning Department at Carnegie Mellon University.  His research spans several topics in AI and machine learning, including work in AI safety and robustness, LLM security, the impact of dat ... Show More
1 h
Jan 2025
Crypto client or cyber trap? [Research Saturday]
Karlo Zanki, Reverse Engineer at ReversingLabs, discussing their work on "Malicious PyPI crypto pay package aiocpa implants infostealer code." ReversingLabs' machine learning-based threat hunting system identified a malicious PyPI package, aiocpa, designed to exfiltrate cryptocur ... Show More
21m 2s
Aug 2024
Threat modeling LLM apps
If you have questions at the intersection of Cybersecurity and AI, you need to know Donato at WithSecure! Donato has been threat modeling AI applications and seriously applying those models in his day-to-day work. He joins us in this episode to discuss his LLM application securit ... Show More
54m 38s
Apr 2025
Google Cloud Chief Information Security Officer on Risk Mitigation
Google Cloud Chief Information Security Officer Phil Venables discusses cybersecurity considerations for open-source large language models and risk mitigation. He speaks with Bloomberg's Carol Massar and Tim Stenovec. See omnystudio.com/listener for privacy information. 
9m 26s