microsoft / fidesLinks
Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.
☆59Updated 5 months ago
Alternatives and similar repositories for fides
Users that are interested in fides are comparing it to the libraries listed below
Sorting:
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆340Updated last week
- LLM proxy to observe and debug what your AI agents are doing.☆52Updated 3 months ago
- Supply chain security for ML☆200Updated last week
- ☆165Updated 4 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆87Updated last year
- ☆49Updated last year
- This is a collection of sidecar containers that can be incorporated within confidential container groups on Azure Container Instances.☆36Updated this week
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…☆86Updated last month
- ☆70Updated 2 weeks ago
- Code for the paper "Defeating Prompt Injections by Design"☆143Updated 4 months ago
- Codebase of https://arxiv.org/abs/2410.14923☆51Updated last year
- This repository is for administrative documents for the CoSAI OASIS Open Project☆63Updated this week
- Proof of concept code for poisoning code generation models.☆53Updated last year
- Guardrails for secure and robust agent development☆362Updated 3 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- Confidential AI samples☆45Updated last year
- ☆123Updated last year
- Universal Robustness Evaluation Toolkit (for Evasion)☆31Updated last month
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆74Updated 3 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆74Updated 2 months ago
- ☆89Updated last year
- The goal of this repo is to become a benchmark for pentesting☆16Updated last year
- The Granite Guardian models are designed to detect risks in prompts and responses.☆119Updated last month
- ☆147Updated 5 months ago
- Cyber-Zero: Training Cybersecurity Agents Without Runtime☆38Updated last week
- Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work☆149Updated last month
- CodeGuard+: Constrained Decoding for Secure Code Generation☆15Updated last year
- The fastest Trust Layer for AI Agents☆144Updated 5 months ago
- ☆35Updated 11 months ago
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆101Updated last year