37th Chaos Communication Congress: New Important Instructions (Video + Slides)
infonewsLLM-Specific
securityresearch
Source: Embrace The RedDecember 30, 2023
Summary
A security researcher presented at the 37th Chaos Communication Congress about Large Language Models Application Security and prompt injection (tricking an AI by hiding instructions in its input). The talk covered security research findings and was made available in video and slide formats for public access.
Classification
Attack Type
Prompt Injection
Attack SophisticationModerate
Impact (CIA+S)
integritysafety
Related Issues
Original source: https://embracethered.com/blog/posts/2023/37c3-new-important-instructions/
First tracked: February 12, 2026 at 02:20 PM
Classified by LLM (prompt v3) · confidence: 85%