↓ Skip to main content
  1. Posts/

The Psychology of Prompt Injection: AI's Social Engineering Problem

·83 words·1 min·
Prompt Injection AI Security Social Engineering Talks
Table of Contents

The Event
#

I spoke at the AWS Offices in London at the AI Exchange covering research exploring a question I had.

I really wanted to explore that since AI/LLMs are created by humans and trained on human data, do they suffer the same psychological vulnerabilities that humans do, and does it align with phishing attacks?

I walk through real examples of how AI systems can fall for the same psychological dispositions humans do.

Watch the full talk: The Psychology of Prompt Injection