Formalizing and Benchmarking Prompt Injection Attacks and Defenses

Understand

A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires.

• Existing works are limited to case studies.
• As a result, the literature lacks a systematic understanding of prompt injection attacks and their defenses.
• We aim to bridge the gap in this work.