TrustAI-laboratory / ASCII-Smuggling-Hidden-Prompt-Injection-DemoLinks
ASCII Smuggling Hidden Prompt Injection is a novel approach to hacking AI assistants using Unicode Tags. This project demostrate how to use Unicode Tags to hide prompt injection instruction to bypass security measures and inject prompts into large language models, such as GPT-4, leading them to provide unintended or harmful responses.
☆14Updated last year
Alternatives and similar repositories for ASCII-Smuggling-Hidden-Prompt-Injection-Demo
Users that are interested in ASCII-Smuggling-Hidden-Prompt-Injection-Demo are comparing it to the libraries listed below
Sorting:
- Codebase of https://arxiv.org/abs/2410.14923☆50Updated 10 months ago
- A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).☆145Updated last year
- An AI-powered application that conducts structured interviews to create and maintain detailed personal profiles across various life aspec…☆48Updated 5 months ago
- A collection of prompt injection mitigation techniques.☆24Updated 2 years ago
- Code for the paper "Defeating Prompt Injections by Design"☆114Updated 3 months ago
- This repository contains various attack against Large Language Models.☆114Updated last year
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆78Updated 4 months ago
- A JupyterLab extension to evaluate the security of your Jupyter environment☆39Updated 2 years ago
- LLM | Security | Operations in one github repo with good links and pictures.☆55Updated 8 months ago
- ATHI — An AI Threat Modeling Framework for Policymakers☆56Updated 2 years ago
- A curated list of awesome LLM Red Teaming training, resources, and tools.☆33Updated 2 weeks ago
- ☆69Updated 3 months ago
- An interactive CLI application for interacting with authenticated Jupyter instances.☆55Updated 4 months ago
- Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems☆205Updated last week
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆168Updated 2 years ago
- Manual Prompt Injection / Red Teaming Tool☆37Updated 11 months ago
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆134Updated 9 months ago
- ☆44Updated last week
- Automated vulnerability discovery and annotation☆67Updated last year
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…☆41Updated 7 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆91Updated last year
- https://arxiv.org/abs/2412.02776☆62Updated 9 months ago
- Do you want to learn AI Security but don't know where to start ? Take a look at this map.☆26Updated last year
- Tree of Attacks (TAP) Jailbreaking Implementation☆115Updated last year
- An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for autho…☆18Updated 4 months ago
- BlueSky OSINT Tool☆14Updated 9 months ago
- ☆30Updated last month
- Machine Learning Attack Series☆68Updated last year
- The fastest Trust Layer for AI Agents☆144Updated 3 months ago
- Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to pote…☆185Updated 5 months ago