PromptInject
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022
agencyenterprise/PromptInject
View on GitHub ↗PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022
PromptInject grew +0.0% in the last 30 days, ranks 15th of 71 in Interpretability & Alignment, last commit 181 days ago.
Star trajectory
116 days tracked+0.0% in 30d, below the Interpretability & Alignment median of +0.2%.
Last commit 181 days ago, fresher than the median of 203d.
How it compares in Interpretability & Alignment
Ranked 15th of 71 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 1
- Forks
- 58
- Watchers
- 10
- Open issues
- 2
- Releases
- 0
- Created
- 2022-10-25
- Stars this week
- -2
You've seen where PromptInject stands today.
Get the moves before everyone else: the 5 Interpretability & Alignment repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.