3min chapter

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

Watermarking Large Language Models to Fight Plagiarism with Tom Goldstein - 621

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

CHAPTER

YOLA Detection

The YOLA detector tries to identify an object in about 20,000 different locations. If any one of those classifiers sees you, you're caught. Fooling an object detector is very hard. We created an adversarial pattern that would essentially work on any person and in any position.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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