aiverify-foundation / moonshot
Moonshot - A simple and modular tool to evaluate and red-team any LLM application.
☆224Updated last week
Alternatives and similar repositories for moonshot:
Users that are interested in moonshot are comparing it to the libraries listed below
- AI Verify☆145Updated this week
- Contains all assets to run with Moonshot Library (Connectors, Datasets and Metrics)☆29Updated this week
- ☆42Updated 8 months ago
- Papers about red teaming LLMs and Multimodal models.☆106Updated 4 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆64Updated 11 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆290Updated 2 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆147Updated last week
- Red-Teaming Language Models with DSPy☆179Updated last month
- TAP: An automated jailbreaking method for black-box LLMs☆162Updated 3 months ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆234Updated 10 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆120Updated this week
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆181Updated 2 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆282Updated 6 months ago
- This repository stems from our paper, “Cataloguing LLM Evaluations”, and serves as a living, collaborative catalogue of LLM evaluation fr…☆17Updated last year
- ☆9Updated last month
- Fiddler Auditor is a tool to evaluate language models.☆178Updated last year
- Tool suite for secure and robust agent development☆175Updated last week
- ☆91Updated last month
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆42Updated this week
- [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`☆64Updated last month
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 10 months ago
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆40Updated 9 months ago
- ☆95Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆285Updated last year
- LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR t…☆409Updated last month
- ☆71Updated 5 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆211Updated 2 months ago
- Improving Alignment and Robustness with Circuit Breakers☆195Updated 6 months ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆356Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆149Updated 11 months ago