microsoft / fidesLinks
Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.
☆66Updated 6 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.☆362Updated last month
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆89Updated last year
- LLM proxy to observe and debug what your AI agents are doing.☆54Updated 3 weeks ago
- ☆49Updated last year
- ☆176Updated 5 months ago
- Supply chain security for ML☆204Updated 2 weeks ago
- This is a collection of sidecar containers that can be incorporated within confidential container groups on Azure Container Instances.☆36Updated last week
- ☆124Updated last year
- ☆74Updated last month
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…☆96Updated last month
- A privacy layer around LLMs☆32Updated last year
- ☆95Updated last year
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- Proof of concept code for poisoning code generation models.☆54Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆75Updated 4 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
- PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents☆26Updated 8 months ago
- Universal Robustness Evaluation Toolkit (for Evasion)☆31Updated 2 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆53Updated 8 months ago
- Confidential AI samples☆46Updated last year
- CodeGuard+: Constrained Decoding for Secure Code Generation☆17Updated last year
- The goal of this repo is to become a benchmark for pentesting☆16Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆77Updated 2 months ago
- LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins☆28Updated last year
- Tools and runtime for launching unmodified container images in Trusted Execution Environments☆153Updated 4 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆172Updated 7 months ago
- ☆31Updated last month
- This repository provides a benchmark for prompt injection attacks and defenses☆346Updated last month
- ☆69Updated 11 months ago
- ☆12Updated last month