Information Flow Control
Type: mitigation
Description: A defense mechanism that allows for information flow control.
Version: 0.1.0
Created At: 2025-03-04 10:27:40 -0500
Last Modified At: 2025-03-04 10:27:40 -0500
External References
- FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks, arXiv
- RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process, arXiv
Related Objects
- --> ChatGPT (platform): Evaluation of the above mitigation strategies leveraged GPT 3.5 and GPT 4.
- <-- LLM Prompt Injection (technique): Information Flow control would be one of many ways to track and control indirect prompt injections from knowledge corruption and leaking sensitive data.