AI-powered OSINT assistant on Hugging Face.

Threat Landscape Copilot - Conversational access to continuously updated, structured threat intelligence.

The Essential AI Toolkit for Journalists and Content Creators, All the tools listed here are free to use and open-source!

LLM vulnerability scanner for probing language models.

Test and evaluate LLM outputs for security and quality.

Python Risk Identification Toolkit for generative AI by Microsoft.

Fuzzing framework for finding vulnerabilities in LLMs.

Collection of real-world AI/ML exploits and vulnerabilities.

Prompt injection detector for LLM applications.

Security toolkit for LLM interactions with input/output filtering.

Toolkit for adding programmable guardrails to LLM applications.

Security best practices for LangChain applications.

Game for testing prompt injection techniques.

Interactive playground for testing prompt injections.

Database of AI system failures and harms.

Python library for adversarial machine learning.

Library for benchmarking ML systems' vulnerability to adversarial examples.

Python toolbox to create adversarial examples.

Framework for adversarial attacks in NLP.

Generic automation layer for assessing security of ML models.

Privacy testing library for deep learning systems.

Tool to audit data privacy in statistical and ML algorithms.

Library for training ML models with differential privacy.

Library for training PyTorch models with differential privacy.

Visualizer for neural network, deep learning, and ML models.

TensorFlow's visualization toolkit.

Model-agnostic visual debugging tool for ML.

Interactive visual interface for ML model analysis.

AI/ML security platform for scanning and protecting models.

AI security and validation platform.

Security platform for AI models and applications.

Enterprise LLM security solution for prompt injections.

ML model monitoring and anomaly detection platform.

ML model performance monitoring and explainability platform.

Collection of ChatGPT jailbreaks and prompts.

Curated list of prompt injection resources.

Resources and research on LLM security vulnerabilities.

Top 10 security risks for LLM applications.

Supply chain security for ML models.

Security features and scanning on Hugging Face Hub.

Streamlines model documentation for transparency.

AI Bill of Materials for tracking AI system components.

Forum for AI alignment and safety research.

Academic papers on AI security.

Curated reading list for AI/ML security.

ML tools and resources for cybersecurity.

Knowledge base of adversarial tactics against ML systems.

Best practices for AI/ML security.