LLM App is a production framework for building and serving AI applications and LLM-enabled real-time data pipelines.

The Security Toolkit for LLM Interactions

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

Papers and resources related to the security and privacy of LLMs 🤖

Prompt injection attacks and defenses in LLM-integrated applications

The world's first open source LLM Applications Firewall.

Risks and targets for assessing LLMs & LLM vulnerabilities

LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins

Framework for Attacking the Confidentiality of Large Language Models (LLMs)

LLM security and privacy

MER is a software that identifies and highlights manipulative communication in text from human conversations and AI-generated responses. MER benchmarks language models for manipulative expressions, fostering development of transparency and safety in AI. It also supports manipulation victims by detecting manipulative patterns in human communication.

Vulnerable LLM Application

This repo focus on how to deal with prompt injection problem faced by LLMs

CLI tool that uses the Lakera API to perform security checks in LLM inputs

The Security Toolkit for LLM Interactions (TS version)

Universal and Transferable Attacks on Aligned Language Models

This project investigates the security of large language models by performing binary classification of a set of input prompts to discover malicious prompts. Several approaches have been analyzed using classical ML algorithms, a trained LLM model, and a fine-tuned LLM model.

The Security Toolkit for LLM Interactions