Security News > 2023 > May > DEF CON to set thousands of hackers loose on LLMs

This year's DEF CON AI Village has invited hackers to show up, dive in, and find bugs and biases in large language models built by OpenAI, Google, Anthropic, and others.

The collaborative event, which AI Village organizers describe as "The largest red teaming exercise ever for any group of AI models," will host "Thousands" of people, including "Hundreds of students from overlooked institutions and communities," all of whom will be tasked with finding flaws in LLMs that power today's chat bots and generative AI. Think: traditional bugs in code, but also problems more specific to machine learning, such as bias, hallucinations, and jailbreaks - all of which ethical and security professionals are now having to grapple with as these technologies scale.

DEF CON is set to run from August 10 to 13 this year in Las Vegas, USA. "Traditionally, companies have solved this problem with specialized red teams. However this work has largely happened in private," said Sven Cattell, the founder of AI Village, in a statement.

How to tell an AI bot wrote that scammy-looking tax email: No spelling mistakes Is your AI hallucinating? Might be time to call in the red team Twitter's AI image-crop algo is biased towards people who look younger, skinnier, and whiter, bounty challenge at DEF CON reveals Slack adding generative AI to interact with colleagues, so you don't have to.

The village people's announcement also mentions this is "With participation from Microsoft," so perhaps hackers will get a go at Bing.

The AI Village hosted its first machine-learning public bias bounty at DEF CON two years ago.

News URL

https://go.theregister.com/feed/www.theregister.com/2023/05/06/ai_hacking_defcon/