Knowledge Return Oriented Prompting (KROP)
On the map: LLM safety and security → Prompt injection and agent security
Abstract (arXiv)
Many Large Language Models (LLMs) and LLM-powered apps deployed today use some form of prompt filter or alignment to protect their integrity. However, these measures aren't foolproof. This paper introduces KROP, a prompt injection technique capable of obfuscating prompt injection attacks, rendering them virtually undetectable to most of these security measures.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. Builds on 5 of its 12 references that are in the map. First posted on arXiv 11 Jun 2024.
Builds on
5 of 12 references.
Closest ancestors · 1
Same direction, newest first
Other references · 4
- 2022Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methodscited by 79
- 2024Safeguarding Large Language Models: A Surveycited by 78
- 2022Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examplescited by 69
- 2024WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Responsecited by 29
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- 2024StruQ: Defending Against Prompt Injection with Structured Queries
- 2024Palisade -- Prompt Injection Detection Framework
- 2024Fine-tuned Large Language Models (LLMs): Improved Prompt Injection Attacks Detection
- 2024Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications
- 2023Jatmo: Prompt Injection Defense by Task-Specific Finetuning
- 2023Prompt Injection attack against LLM-integrated Applications
- 2025Defending Against Prompt Injection With a Few DefensiveTokens