ml-safety topic

🐢 Open-Source Evaluation & Testing for ML & LLM systems

Giskard-AI

[ICML 2019] ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

YyzHarry

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 Sa...

agencyenterprise

📚 A curated list of papers & technical articles on AI Quality & Safety

Giskard-AI

Deliver safe & effective language models

Pacific-AI-Corp

Predicting Out-of-Distribution Error with the Projection Norm

yaodongyu