Made a tool simulating how Google's CaMeL protects AI systems from prompt injection by using capability-based security instead of hoping the AI "behaves."

Link to the Google paper: https://arxiv.org/pdf/2503.18813v1

All credit to the researchers.

@misc{debenedetti2025defeatingpromptinjectionsdesign, title={Defeating Prompt Injections by Design}, author={Edoardo Debenedetti and Ilia Shumailov and Tianqi Fan and Jamie Hayes and Nicholas Carlini and Daniel Fabian and Christoph Kern and Chongyang Shi and Andreas Terzis and Florian Tramèr}, year={2025}, eprint={2503.18813}, archivePrefix={arXiv}, primaryClass={cs.CR}, url={https://arxiv.org/abs/2503.18813}, }