SS-NEWS-114: AI Cannot Be Trusted

Episode 114 June 05, 2023 00:49:21
SS-NEWS-114: AI Cannot Be Trusted
Security Serengeti
SS-NEWS-114: AI Cannot Be Trusted

Jun 05 2023 | 00:49:21

/

Show Notes

This week, we have three related AI articles all dealing with trust, or lack thereof, in the results AI so confidently gives you.  This can range from poisoning of the training data to confident hallucinations, to faking interviews.  It's a brave new world out there.

Article 1 - The poisoning of ChatGPT

Article 2 - Lawyer cited 6 fake cases made up by ChatGPT; judge calls it “unprecedented”
Supporting Articles:
Professor Flunks All His Students After ChatGPT Falsely Claims It Wrote Their Papers

Article 3 - Github - Ecoute

If you found this interesting or useful, please follow us on Twitter @serengetisec and subscribe and review on your favorite podcast app!

Other Episodes

Episode 123

August 21, 2023 00:44:38
Episode Cover

SS-REVW-123: Defcon and Black Hat Trip Report!

Matthew has returned from Hacker Summer Camp, full of stories and information about new technology.  So sit with us for a while, and listen...

Listen

Episode 138

March 11, 2024 00:54:52
Episode Cover

SS-BOOK-138: All Your Face Are Belong To Us

This week we take a look at a book that's been making the podcast rounds - Your Face Belongs to Us by Kashmir Hill. ...

Listen

Episode 64

June 06, 2022 00:35:20
Episode Cover

SS-NEWS-064: Social Engineering Kill Chain Model!

In this episode, we discuss a Kill Chain-like model for Social Engineering attacks.  We were going to do two articles, but we went deep. ...

Listen