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
Analyze how language models respond to tricky prompts to improve their reliability and safety.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimePromptInject 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 has 528 stars on GitHub. It has been forked 58 times. PromptInject is written mainly in Python. It has been in active development since 2022. PromptInject is available under the MIT license. Its main topics are adversarial-attacks, agi, agi-alignment, ai-alignment.
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 is an open-source project. It is released under the MIT license.
Yes. PromptInject is free and open source — you can use, modify and self-host it.
PromptInject is available under the MIT license.
PromptInject is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/agencyenterprise-promptinject.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.