Adding guardrails to large language models.

An adversarial example library for constructing attacks, building defenses, and benchmarking both

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

SecLists is the security tester's companion. It's a collection of multiple types of lists used during security assessments, collected in one place. List types include usernames, passwords, URLs, se…

A list of useful payloads and bypass for Web Application Security and Pentest/CTF

Automatic SQL injection and database takeover tool

An interactive TLS-capable intercepting HTTP proxy for penetration testers and software developers.

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

Examples and guides for using the OpenAI API

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)

structured outputs for llms

The Security Toolkit for LLM Interactions

A Python pickling decompiler and static analyzer

Simple, safe way to store and distribute tensors

Training PyTorch models with differential privacy

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities

the LLM vulnerability scanner