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 134

February 26, 2024 00:50:58
Episode Cover

SS-RPRT-137: The Blue Report

This week we take a look at the Picus Security Blue Report, and provide some analysis of the statements.  Interesting findings here.  The report...

Listen

Episode 36

November 21, 2021 00:39:41
Episode Cover

SS-SUBJ-36: Breach and Attack Simulation

In this episode, we discuss one of our favorite tools to come out, Breach and Attack Simulation.  I hope you can tell we both...

Listen

Episode 32

October 24, 2021 00:24:17
Episode Cover

SS-CONF-32: Splunk .conf 21, Part 1

In this episode, we talk .Conf!  David and I attended Splunk .conf remotely and sit down to discuss this years presentations and announcements.  Unfortunately,...

Listen