BenderScript / PromptInjectionBenchLinks
Prompt Injection Attacks against GPT-4, Gemini, Azure, Azure with Jailbreak
β23Updated 8 months ago
Alternatives and similar repositories for PromptInjectionBench
Users that are interested in PromptInjectionBench are comparing it to the libraries listed below
Sorting:
- π€π‘οΈπππ Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.β23Updated last year
- A knowledge source about TTPs used to target GenAI-based systems, copilots and agentsβ38Updated last week
- A curated list of awesome LLM Red Teaming training, resources, and tools.β17Updated 3 months ago
- IOCs from zLabs researchβ20Updated last week
- Web app tool for helping compose advance search operators (aka Google dorking AKA boolean searches) for a variety of search enginesβ37Updated 2 years ago
- A powerful Python script that allows you to scrape messages and media from Telegram channels using the Telethon library. Features includeβ¦β11Updated last month
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victβ¦β42Updated 4 months ago
- MINOTAUR: The STRONGEST Secure Prompt EVER! Prompt Security Challenge, Impossible GPT Security, Prompts Cybersecurity, Prompting Vulnerabβ¦β16Updated last year
- A curated list of GPT agents for cybersecurityβ10Updated 8 months ago
- β21Updated 3 months ago
- OSINT Eye Mobileβ15Updated 4 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)β88Updated last year
- Jailbroken Geminiβ19Updated last year
- Codebase of https://arxiv.org/abs/2410.14923β48Updated 8 months ago
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whiβ¦β42Updated 10 months ago
- Manual Prompt Injection / Red Teaming Toolβ31Updated 8 months ago
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. β¦β52Updated last year
- This repository provides a benchmark for prompt Injection attacks and defensesβ232Updated 3 weeks ago
- A collection of prompt injection mitigation techniques.β22Updated last year
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)β120Updated 6 months ago
- Penetration Testing AI Assistant based on open source LLMs.β84Updated 2 months ago
- Payloads for Attacking Large Language Modelsβ90Updated 3 weeks ago
- [SPOILER ALERT] Solutions to Gandalf, the prompt hacking/red teaming game from Lakera AIβ25Updated last year
- OpenAI Security Console - Python3 AI-powered Cybersecurity Frameworkβ17Updated 2 years ago
- Code for the website www.jailbreakchat.comβ96Updated last year
- A comprehensive collection of CyberSecurity PDFs. Guides, Research Papers, Education, Information Security, Network Security, Cryptographβ¦β32Updated 9 months ago
- A (not too) Evil Chatbot πΉβ50Updated last year
- My inputs for the LLM Gandalf made by Lakeraβ43Updated last year
- β14Updated 6 months ago
- The goal of this repository is to work with Whiterabbitneo with PentestGPTβ38Updated last year