6min chapter

MLOps.community  cover image

Robustness, Detectability, and Data Privacy in AI // Vinu Sankar Sadasivan // #289

MLOps.community

CHAPTER

Advancements in AI Vulnerability Exploitation

This chapter explores the complexities of automated attacks on language models, particularly focusing on the GCG algorithm and how adversaries can manipulate inputs to cause malfunctions. It also discusses transferability of adversarial attacks between models and the defensive strategies being employed, such as automated red teaming and the use of classifiers.

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