hupe1980 / aisploit
π€π‘οΈπππ Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.
β16Updated 6 months ago
Related projects β
Alternatives and complementary repositories for aisploit
- β62Updated last month
- β36Updated this week
- This is a dataset intended to train a LLM model for a completely CVE focused input and output.β44Updated last week
- A collection of prompt injection mitigation techniques.β18Updated last year
- Chat4GPT Experiments for Securityβ11Updated last year
- SecGPT: An execution isolation architecture for LLM-based systemsβ49Updated 3 weeks ago
- Whispers in the Machine: Confidentiality in LLM-integrated Systemsβ29Updated 2 weeks ago
- β24Updated 2 months ago
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whiβ¦β23Updated 3 months ago
- Hodor for node.jsβ13Updated last year
- β22Updated last month
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victβ¦β41Updated 7 months ago
- The system consists of multiple AI agents that collaborate to strategize, generate commands, and execute scans based on the client's descβ¦β31Updated 7 months ago
- A library to produce cybersecurity exploitation routes (exploit flows). Inspired by TensorFlow.β29Updated last year
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.β26Updated last week
- Payloads for Attacking Large Language Modelsβ64Updated 4 months ago
- future-proof vulnerability detection benchmark, based on CVEs in open-source reposβ44Updated last week
- β26Updated this week
- All things specific to LLM Red Teaming Generative AIβ14Updated last month
- β20Updated last year
- β19Updated last year
- Tree of Attacks (TAP) Jailbreaking Implementationβ95Updated 9 months ago
- AI-based Web Application Penetration Testing Toolβ18Updated 10 months ago
- A collection of agents that use Large Language Models (LLMs) to perform tasks common on our day to day jobs in cyber security.β56Updated 6 months ago
- Automatically fuzz Rust projects from scratchβ54Updated 6 months ago
- Exploits of different CVE IDs (CVE-2021-37910, CVE-2021-40288, CVE-2021-41435, CVE-2021-41436, CVE-2021-41437, CVE-2021-41441, CVE-2021-4β¦β16Updated 2 years ago
- β16Updated 5 months ago
- Prompt Injections Everywhereβ85Updated 3 months ago
- A framework for identifying vulnerabilities in VS Code extensionsβ15Updated 4 months ago
- keep watching new bug bounty (vulnerability) postings.β12Updated 7 months ago