Topic: prompt-injection Goto Github
Some thing interesting about prompt-injection
Some thing interesting about prompt-injection
prompt-injection,Curated + custom prompt injections.
User: 2alf
Home Page: https://xladn0.rf.gd/work/notes/half20/
prompt-injection,AI/LLM Prompt Injection List is a curated collection of prompts designed for testing AI or Large Language Models (LLMs) for prompt injection vulnerabilities. This list aims to provide a comprehensive set of prompts that can be used to evaluate the behavior of AI or LLM systems when exposed to different types of inputs.
User: anthenamatrix
Home Page: https://anthenamatrix.com
prompt-injection,ASCII Art Prompt Injection is a novel approach to hacking AI assistants using ASCII art. This project leverages the distracting nature of ASCII art to bypass security measures and inject prompts into large language models, such as GPT-4, leading them to provide unintended or harmful responses.
User: anthenamatrix
Home Page: https://anthenamatrix.com
prompt-injection,Image Prompt Injection is a Python script that demonstrates how to embed a secret prompt within an image using steganography techniques. This hidden prompt can be later extracted by an AI system for analysis, enabling covert communication with AI models through images.
User: anthenamatrix
Home Page: https://anthenamatrix.com
prompt-injection,The Prompt Injection Testing Tool is a Python script designed to assess the security of your AI system's prompt handling against a predefined list of user prompts commonly used for injection attacks. This tool utilizes the OpenAI GPT-3.5 model to generate responses to system-user prompt pairs and outputs the results to a CSV file for analysis.
User: anthenamatrix
Home Page: https://anthenamatrix.com
prompt-injection,Website Prompt Injection is a concept that allows for the injection of prompts into an AI system via a website's. This technique exploits the interaction between users, websites, and AI systems to execute specific prompts that influence AI behavior.
User: anthenamatrix
Home Page: https://anthenamatrix.com
prompt-injection,Self-hardening firewall for large language models
Organization: automorphic-ai
Home Page: https://automorphic.ai
prompt-injection,A new kind of MLOps platform purpose built for production generative ai apps
Organization: costly-ai
Home Page: https://costly.ai
prompt-injection,This project leverages the SDXL-Turbo model for versatile image processing tasks. Offering a simple command-line interface, it facilitates both Text-to-image and Image-to-image operations. Users select an operation, input prompts, and the script dynamically generates and executes code snippets.
User: cursedprograms
Home Page: https://cursedprograms.github.io/Image-Generator/
prompt-injection,LLM prompt injection detection
User: cutwell
prompt-injection,ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security, Super Prompts, Prompt Hack, Prompt Security, Ai Prompt Engineering, Adversarial Machine Learning.
User: cyberalbsecop
prompt-injection,Bullet-proof your custom GPT system prompt security with KEVLAR, the ultimate prompt protector against rules extraction, prompt injections, and leaks of AI agent secret instructions.
User: cyberalbsecop
Home Page: https://flowgpt.com/p/kevlar-anti-leak-system-prompts
prompt-injection,MINOTAUR: The STRONGEST Secure Prompt EVER! Prompt Security Challenge, Impossible GPT Security, Prompts Cybersecurity, Prompting Vulnerabilities, FlowGPT, Secure Prompting, Secure LLMs, Prompt Hacker, Cutting-edge Ai Security, Unbreakable GPT Agent, Anti GPT Leak, System Prompt Security.
User: cyberalbsecop
Home Page: https://flowgpt.com/p/minotaur-impossible-security-challenge
prompt-injection,⥠Vigil ⥠Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
User: deadbits
Home Page: https://vigil.deadbits.ai/
prompt-injection,Dropbox LLM Security research code and results
Organization: dropbox
prompt-injection,My inputs for the LLM Gandalf made by Lakera
User: gdalmau
Home Page: https://gandalf.lakera.ai/
prompt-injection,Client SDK to send LLM interactions to Vibranium Dome
Organization: genia-dev
Home Page: https://docs.vibraniumdome.com
prompt-injection,Build production ready apps for GPT using Node.js & TypeScript
Organization: gptsafe
prompt-injection,A prompt injection game to collect data for robust ML research
Organization: humancompatibleai
Home Page: https://tensortrust.ai/paper
prompt-injection,Repo hosting the data and results of my research on LLM prompt injection resistance.
User: juicete4
prompt-injection,Guard your LangChain applications against prompt injection with Lakera ChainGuard.
Organization: lakeraai
Home Page: https://lakeraai.github.io/chainguard/
prompt-injection,A benchmark for prompt injection detection systems.
Organization: lakeraai
prompt-injection, Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.
Organization: langgptai
prompt-injection,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.
Organization: levitation-opensource
Home Page: https://www.simplify.ee/
prompt-injection,Prompt injection attacks and defenses in LLM-integrated applications
User: liu00222
prompt-injection,Whispers in the Machine: Confidentiality in LLM-integrated Systems
User: lostoxygen
prompt-injection,Vulnerable LLM Application
User: m507
Home Page: https://shellcode.blog/llm1/
prompt-injection,A Python package designed to detect prompt injection in text inputs utilizing state-of-the-art machine learning models from Hugging Face. The main focus is on ease of use, enabling developers to integrate security features into their applications with minimal effort.
User: maxmlang
prompt-injection,Turning Gandalf against itself. Use LLMs to automate playing Lakera Gandalf challenge without needing to set up an account with a platform provider.
Organization: microsoft
prompt-injection,Happy Prompt is a unique tool designed to interject positive emotions into text prompts, allowing users to communicate joyful, uplifting, and enthusiastic expressions. It utilizes a series of cheerful emojis, symbols, and text representations to infuse the text with a sense of happiness, love, dancing, partying, and other upbeat themes.
User: milosilo
Home Page: https://milosilo.com/happy-prompt/
prompt-injection,Prompt Engineering Tool for AI Models with cli prompt or api usage
User: milosilo
Home Page: https://milosilo.com/hacking/ai-cognitive-behavioral-analysis-for-prompt-engineering-using-ratemyai/
prompt-injection,The Security Toolkit for LLM Interactions (TS version)
Organization: nodite
prompt-injection,The Security Toolkit for LLM Interactions
Organization: protectai
Home Page: https://llm-guard.com/
prompt-injection,LLM Prompt Injection Detector
Organization: protectai
Home Page: https://playground.rebuff.ai
prompt-injection,A serverless set of functions for evaluating whether incoming messages to an LLM system seem to contain instances of prompt injection; uses cascading cosine similarity and ROUGLE-L calculation against known good and bad prompts
User: rabbidave
prompt-injection,This repo focus on how to deal with prompt injection problem faced by LLMs
User: rohilrg
prompt-injection,A prompt defence is a multi-layer defence that can be used to protect your applications against prompt injection attacks.
Organization: safetorun
Home Page: https://promptshield.readme.io
prompt-injection,The Security Toolkit for managing Generative AI(especially LLMs) and Supervised Learning processes(Learning and Inference).
User: semanticbraincorp
Home Page: https://www.semanticbrain.net
prompt-injection,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.
User: sinanw
prompt-injection,Prompimix(PromptCrafter/ tp-cooker) is an innovative software application developed using JavaScript, CSS, and HTML, designed to streamline the process of creating text-to-image prompts. This intuitive web-based tool empowers users to effortlessly generate captivating visual prompts for a variety of applications.
User: tacoen
Home Page: https://tacoen.github.io/prompimix/
prompt-injection,Every practical and proposed defense against prompt injection.
User: tldrsec
Home Page: https://tldrsec.com/subscribe
prompt-injection,automatically tests prompt injection attacks on ChatGPT instances
User: utkusen
prompt-injection,Let Raccoon sample the unknown, safeguarding your AI's home.
User: velocitatem
Home Page: https://llm-cps.streamlit.app/
prompt-injection,ChatGPT Adversarial Attack for The Pitt Challenge 2023
User: vivswan
Home Page: http://pittchallenge.com
prompt-injection,đ LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). đ Extracts signals from prompts & responses, ensuring safety & security. đĄď¸ Features include text quality, relevance metrics, & sentiment analysis. đ A comprehensive tool for LLM observability. đ
Organization: whylabs
Home Page: https://whylabs.ai
prompt-injection,prompt attack-defense, prompt Injection, reverse engineering notes and examples | ć示čŻĺŻšćăç ´č§Łäžĺä¸çŹčŽ°
User: yunwei37
prompt-injection,My solutions for Lakera's Gandalf
User: zapdos7
Home Page: https://gandalf.lakera.ai/
A declarative, efficient, and flexible JavaScript library for building user interfaces.
đ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. đđđ
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google â¤ď¸ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.