AlphaUncommon
agencyenterprise/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
- Owner
- agencyenterprise (organization)
- Stars
- Stars: 528
- Forks
- Forks: 59
- Language
- Python
- License
- MIT
- Created
- 2022
- Topics
- ai-safetylanguage-modelsml-safetyagiai-alignmentagi-alignmentadversarial-attacksgpt-3large-language-modelsmachine-learning
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by agencyenterprise
All 3 repos by agencyenterprise- agencyenterprise/react-native-healthStars: 1,163Objective-CBeta
- agencyenterprise/neurotechdevkitStars: 143PythonPrototype
Nearby in Python
All Python repos- soul-99/SU_IMDStars: 528PythonAlpha
- Adkid-Zephyr/oral-paper-skillStars: 528PythonAlpha
- RosettaCommons/RFD4-ProteinaStars: 528PythonAlpha
- styxit/HTPC-ManagerStars: 528PythonAlpha
- wakatime/sublime-wakatimeStars: 528PythonAlpha
- vitorfs/parsifalStars: 528PythonAlpha