Threat Landscape

Unveiling AI Agent Vulnerabilities Part III: Data Exfiltration

13 de мая de 2025

In the third part of our series we demonstrate how risk intensifies in multi-modal AI agents, where hidden instructions embedded within innocuous-looking images or documents can trigger sensitive data exfiltration without any user interaction.

Ознакомиться со статьей  

  • страницы:
  • 1
  • 2
  • 3
  • 4
  • 5
  • страницы:
  • 1
  • 2
  • 3
  • 4
  • 5