OWASP Top 10 for Large Language Model Applications | OWASP Foundation
Aims to educate developers, designers, architects, managers, and organizations about the potential security risks when deploying and managing Large Language Models (LLMs)

OWASP LLM Top 10 -  Full Report Version 1.0
Prevention and Remediation recommendations can also be found within this OWASP report

OWASP LLM Top 10 Website  

Prompt Tuning - IBM Research Blog
‍
Chat Arena - Prompt Testing Tool
‍
LLM Hacker Handbook

The Prompt Report - Jailbreak Chat

doublespeak.chat - a text-based AI escape game by Forces Unseen.

‍Project Website
‍
Project Github Downloads and Documentation

Contact us:  LLMcanarybenchmark@gmail.com ‍

AI Risk Management Standards Profile for GPAIS, Center for Long-term Cybersecurity (CLTC), https://cltc.berkeley.edu/wp-content/uploads/2023/11/Berkeley-GPAIS-Foundation-Model-Risk-Management-Standards-Profile-v1.0.pdf

LLM Survey Report. MLOps. 2023.  https://mlops.community/wp-content/uploads/2023/07/survey-report-MLOPS-v16-FINAL.pdf

Franzen C. More than 70% of companies are experimenting with generative AI, but few are willing to commit more spending. Venture Beat. July 25, 2023. https://venturebeat.com/ai/more-than-70-of-companies-are-experimenting-with-generative-ai-but-few-are-willing-to-commit-more-spending/

Zou A., et. al. Universal and Transferable Adversarial Attacks on Aligned Language Models. Arxiv:2211.09110 [cs.CL]. July 27, 2023. https://arxiv.org/abs/2307.15043, alt. https://llm-attacks.org/

Liang P., et. al. Holistic Evaluation of Language Models (HELM). Arxvix:2307.15043 [cs.CL]. November 16, 2023. https://arxiv.org/abs/2211.09110, alt. https://crfm.stanford.edu/helm/latest/