EPISODE · Apr 30, 2025 · 3 MIN
All Major Gen-AI Models Vulnerable to ‘Policy Puppetry’ Prompt Injection Attack
from RADIO 007 · host RADIO007
A new attack technique named Policy Puppetry can break the protections of major gen-AI models to produce harmful outputs.
What this episode covers
A new attack technique named Policy Puppetry can break the protections of major gen-AI models to produce harmful outputs.
NOW PLAYING
All Major Gen-AI Models Vulnerable to ‘Policy Puppetry’ Prompt Injection Attack
0:00
3:04
1×
No transcript for this episode yet
Similar Episodes
Similar Podcasts
La Corrobra
Canal Extremadura
El espacio de la radio pública que pone en valor las lenguas autóctonas de Extremadura: el estremeñu, la fala y el portugués rayano.Con Juan Pedro Sánchez.
Radio Maria Kenya
Radio Maria Kenya
A Christian voice in Kenya and in the World
The Brackenfield Records
Anvil Audio Productions
An off-beat homage to classic radio detectives of the 1940s and '50s, The Brackenfield Records offers comforting genre fare, sitting somewhere between cosy and hard-boiled crime fiction.Whether it's dealing with unfaithful spouses, off-the-rails celebrities, crooked businesspeople, or gun-toting no-gooders, Brackenfield never falters!
DarkCompass
Hard Rock Hell Radio
DarkCompass brings you some of the best New Independent and Unsigned Music Every Week, from around the world.
Frequently Asked Questions
How long is this episode of RADIO 007?
This episode is 3 minutes long.
When was this RADIO 007 episode published?
This episode was published on April 30, 2025.
What is this episode about?
A new attack technique named Policy Puppetry can break the protections of major gen-AI models to produce harmful outputs.
Can I download this RADIO 007 episode?
Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!