Reapor-Yurnero / imprompterLinks
Codebase of https://arxiv.org/abs/2410.14923
☆47Updated 7 months ago
Alternatives and similar repositories for imprompter
Users that are interested in imprompter are comparing it to the libraries listed below
Sorting:
- A collection of prompt injection mitigation techniques.☆23Updated last year
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆113Updated 5 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated last year
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆68Updated last week
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆87Updated last year
- Tree of Attacks (TAP) Jailbreaking Implementation☆109Updated last year
- ☆109Updated 2 weeks ago
- Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to pote…☆168Updated 2 months ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆46Updated 6 months ago
- An interactive CLI application for interacting with authenticated Jupyter instances.☆53Updated 3 weeks ago
- Top 10 for Agentic AI (AI Agent Security)☆110Updated last week
- A utility to inspect, validate, sign and verify machine learning model files.☆57Updated 4 months ago
- Dropbox LLM Security research code and results☆228Updated last year
- ☆34Updated 6 months ago
- ☆44Updated last month
- ☆14Updated 5 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆110Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆68Updated last year
- Payloads for Attacking Large Language Models☆89Updated 10 months ago
- Manual Prompt Injection / Red Teaming Tool☆31Updated 8 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆56Updated 2 months ago
- future-proof vulnerability detection benchmark, based on CVEs in open-source repos☆56Updated last week
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …☆49Updated last year
- ☆43Updated last week
- General research for Dreadnode☆23Updated 11 months ago
- A benchmark for prompt injection detection systems.☆115Updated 3 weeks ago
- ☆40Updated 5 months ago
- A very simple open source implementation of Google's Project Naptime☆150Updated 2 months ago
- https://arxiv.org/abs/2412.02776☆54Updated 6 months ago
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…☆42Updated 3 months ago