The Security Toolkit for LLM Interactions

a security scanner for custom LLM applications

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

Self-hardening firewall for large language models

This repository provides a benchmark for prompt Injection attacks and defenses

Dropbox LLM Security research code and results

gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR和TTS的开源框架。

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

Code scanner to check for issues in prompts and LLM calls

A prompt injection game to collect data for robust ML research

The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails.

PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It includes 10 hands-on challenges inspired by the OWASP LLM Top 10, demonstrating how these vulnerabilities can be discovered and exploited in real-world scenarios.

This class is a broad overview and dive into Exploiting AI and the different attacks that exist, and best practice strategies.

RAG/LLM Security Scanner identifies critical vulnerabilities in AI-powered applications, including chatbots, virtual assistants, and knowledge retrieval systems.

Whispers in the Machine: Confidentiality in Agentic Systems

Manual Prompt Injection / Red Teaming Tool

Easy to use LLM Prompt Injection Detection / Detector Python Package

The Security Toolkit for managing Generative AI(especially LLMs) and Supervised Learning processes(Learning and Inference).

LLM Security Platform.

Improving AI Systems with Self-Defense Mechanisms