mithril-security / blindboxLinks
BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps
☆61Updated last year
Alternatives and similar repositories for blindbox
Users that are interested in blindbox are comparing it to the libraries listed below
Sorting:
- Supply chain security for ML☆192Updated this week
- A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).☆145Updated last year
- Zero-trust AI APIs for easy and private consumption of open-source LLMs☆40Updated last year
- Your buddy in the (L)LM space.☆64Updated 11 months ago
- Test Software for the Characterization of AI Technologies☆262Updated this week
- Red-Teaming Language Models with DSPy☆213Updated 7 months ago
- 📚 A curated list of papers & technical articles on AI Quality & Safety☆192Updated 5 months ago
- Masked Python SDK wrapper for OpenAI API. Use public LLM APIs securely.☆119Updated 2 years ago
- Lightweight LLM Interaction Framework☆375Updated this week
- A fully in-browser privacy solution to make Conversational AI privacy-friendly☆229Updated 11 months ago
- Code for the paper "Defeating Prompt Injections by Design"☆114Updated 2 months ago
- An open-source compliance-centered evaluation framework for Generative AI models☆163Updated last week
- This repository contains code to generate and preprocess Learning with Errors (LWE) data and implementations of four LWE attacks uSVP, SA…☆53Updated 4 months ago
- AgentFence is an open-source platform for automatically testing AI agent security. It identifies vulnerabilities such as prompt injection…☆25Updated 6 months ago
- LLM-powered autonomous agent with hierarchical task management☆51Updated 2 years ago
- The AILuminate v1.1 benchmark suite is an AI risk assessment benchmark developed with broad involvement from leading AI companies, academ…☆23Updated 3 months ago
- Thorn in a HaizeStack test for evaluating long-context adversarial robustness.☆26Updated last year
- Fiddler Auditor is a tool to evaluate language models.☆187Updated last year
- Security and compliance proxy for LLM APIs☆48Updated 2 years ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆96Updated 5 months ago
- Chat Markup Language conversation library☆55Updated last year
- Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and min…☆26Updated 10 months ago
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆55Updated 6 months ago
- The Granite Guardian models are designed to detect risks in prompts and responses.☆112Updated last week
- The fastest Trust Layer for AI Agents☆144Updated 3 months ago
- Examples scripts that showcase how to use Private AI Text to de-identify, redact, hash, tokenize, mask and synthesize PII in text.☆84Updated 4 months ago
- Practical examples of "Flawed Machine Learning Security" together with ML Security best practice across the end to end stages of the mach…☆119Updated 3 years ago
- Graphsignal Tracer for Python☆205Updated last week
- LLM plugin for models hosted by Anyscale Endpoints☆35Updated last year
- Constrain LLM output☆113Updated last year