Interesting Paper Exploring Prompt Injection
High
Summary
This is a fascinating explotation of how LLMs fall for prompt injection attacks. It turns out that they learn to recognize the style of text in different role/instruction blocks, and not just the tags. Their conclusion: Role tags were a formatting trick that became the security architecture and the cognitive scaffoldin
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data