safellama / plexiglassLinks
A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
☆151Updated last year
Alternatives and similar repositories for plexiglass
Users that are interested in plexiglass are comparing it to the libraries listed below
Sorting:
- The fastest Trust Layer for AI Agents☆145Updated 6 months ago
- Red-Teaming Language Models with DSPy☆238Updated 9 months ago
- Fiddler Auditor is a tool to evaluate language models.☆188Updated last year
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆430Updated last year
- Dropbox LLM Security research code and results☆245Updated last year
- Test Software for the Characterization of AI Technologies☆265Updated this week
- Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems☆218Updated 2 months ago
- A JupyterLab extension to evaluate the security of your Jupyter environment☆39Updated 2 years ago
- Lightweight LLM Interaction Framework☆394Updated last week
- An open-source compliance-centered evaluation framework for Generative AI models☆172Updated 2 weeks ago
- Code for the paper "Defeating Prompt Injections by Design"☆151Updated 5 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆99Updated 7 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…☆437Updated last year
- source for llmsec.net☆16Updated last year
- Curation of prompts that are known to be adversarial to large language models☆186Updated 2 years ago
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆176Updated 2 years ago
- Machine Learning Attack Series☆70Updated last year
- AgentFence is an open-source platform for automatically testing AI agent security. It identifies vulnerabilities such as prompt injection…☆42Updated 8 months ago
- A collection of prompt injection mitigation techniques.☆24Updated 2 years ago
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆591Updated 2 months ago
- BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps☆62Updated 2 years ago
- A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.☆399Updated 3 months ago
- A benchmark for prompt injection detection systems.☆150Updated 3 months ago
- [Corca / ML] Automatically solved Gandalf AI with LLM☆52Updated 2 years ago
- Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to pote…☆191Updated last month
- Payloads for Attacking Large Language Models☆106Updated 5 months ago
- ATLAS tactics, techniques, and case studies data☆88Updated this week
- 📚 A curated list of papers & technical articles on AI Quality & Safety☆193Updated 7 months ago
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …☆58Updated last year
- Secure Jupyter Notebooks and Experimentation Environment☆84Updated 9 months ago