Cyberveillecurated by Decio
Nuage de tags
Mur d'images
Quotidien
Flux RSS
  • Flux RSS
  • Daily Feed
  • Weekly Feed
  • Monthly Feed
Filtres

Liens par page

  • 20 links
  • 50 links
  • 100 links

Filtres

Untagged links
1 résultat taggé Policy-Puppetry  ✕
All Major Gen-AI Models Vulnerable to ‘Policy Puppetry’ Prompt Injection Attack https://www.securityweek.com/all-major-gen-ai-models-vulnerable-to-policy-puppetry-prompt-injection-attack/
25/04/2025 21:42:03
QRCode
archive.org

A new attack technique named Policy Puppetry can break the protections of major gen-AI models to produce harmful outputs.

securityweek EN 2025 technique Gen-AI Models Policy-Puppetry AI vulnerabilty
4470 links
Shaarli - The personal, minimalist, super-fast, database free, bookmarking service par la communauté Shaarli - Theme by kalvn - Curated by Decio