CrowdStrike Uncovers New Prompt Injection Techniques
ID: 7fbc41d4-6e1a-5ad7-8022-68d809838e8b
STIX ID: report--7fbc41d4-6e1a-5ad7-8022-68d809838e8b
Feed Name: Crowdstrike Blog
CrowdStrike announces 18 additions to its prompt-injection taxonomy (bringing coverage to over 200 techniques), highlights five new techniques (Trigger-Activated Rule Addition, Cognitive Token Suppression, Algorithmic Payload Decomposition, Special Token Injection, and Unwitting User Delivery), outlines implications for AI security teams, and promotes Falcon AIDR and related resources to detect and mitigate prompt-injection risks.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.