facebookresearch / privacy_adversarial_framework
The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspired by MITRE ATT&CK®.
☆55Updated last year
Alternatives and similar repositories for privacy_adversarial_framework
Users that are interested in privacy_adversarial_framework are comparing it to the libraries listed below
Sorting:
- Tree of Attacks (TAP) Jailbreaking Implementation☆108Updated last year
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 11 months ago
- using ML models for red teaming☆43Updated last year
- Data Scientists Go To Jupyter☆63Updated 2 months ago
- A knowledge source about TTPs used to target GenAI-based systems, copilots and agents☆35Updated 2 months ago
- ☆21Updated 3 weeks ago
- A collection of prompt injection mitigation techniques.☆22Updated last year
- ReconPal: Leveraging NLP for Infosec☆56Updated 2 years ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆109Updated last year
- Explore AI Supply Chain Risk with the AI Risk Database☆56Updated last year
- ☆130Updated this week
- 🤖 A GitHub action that leverages fabric patterns through an agent-based approach☆26Updated 4 months ago
- ☆40Updated last week
- Codebase of https://arxiv.org/abs/2410.14923☆47Updated 6 months ago
- ATLAS tactics, techniques, and case studies data☆71Updated 3 weeks ago
- General research for Dreadnode☆23Updated 10 months ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆71Updated 2 weeks ago
- Cont3xt intends to centralize and simplify a structured approach to gathering contextual intelligence in support of technical investigati…☆37Updated last year
- This repository is dedicated to providing comprehensive mappings of the OWASP Top 10 vulnerabilities for Large Language Models (LLMs) to …☆13Updated last year
- An interactive CLI application for interacting with authenticated Jupyter instances.☆53Updated last week
- LLM Testing Findings Templates☆72Updated last year
- Source code of "TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification", ACL2024 (findings)☆11Updated 5 months ago
- ☆104Updated 11 months ago
- A utility to inspect, validate, sign and verify machine learning model files.☆57Updated 3 months ago
- Dragon-GPT uses Chat-GPT, or local LLM, to execute automatic and AI-powered threat modeling analysis on a given OWASP Threat Dragon diagr…☆35Updated 2 months ago
- Central repo for talks and presentations☆46Updated 9 months ago
- future-proof vulnerability detection benchmark, based on CVEs in open-source repos☆52Updated last week
- 🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.☆23Updated last year
- Project LLM Verification Standard☆43Updated last year
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆41Updated 8 months ago