AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
23min chapter
Cryptanalyzing LLMs with Nicholas Carlini
Security Cryptography Whatever
Defending Language Models: Risks and Strategies
This chapter explores the vulnerabilities of language models to training data extraction attacks and discusses methods to distinguish between original outputs and leaked information. The conversation covers normalization techniques, defense strategies against data poisoning, and image manipulation techniques to protect artistic integrity. Additionally, it highlights the need for critical evaluation of current security practices and the importance of adapting to evolving threats in the digital landscape.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode