#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

LLM based map for research, exploration and discovery.
Zero shot vulnerability discovery using LLMs

Meet Eclipse the only jailbreak that moonwalks around ChatGPT 4o.

Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

Repository of AI-generated Nuclei templates for public CVEs not yet covered by existing templates, enhancing detection speed and coverage 👾

Technical Details and Exploit for CVE-2024-11394

A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities

Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models

Proof-of-concept demonstrating prompt injection in Langchain's GraphCypherQAChain leading to SQL injection in Neo4j databases. Includes Docker-based…

A small go harness that uses Ollama to orchestrate LLMs in a restricted process flow

Curated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…

The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)

Real-time deepfake toolkit for penetration testing of identity verification and video conferencing systems. Supports face swap, image animation, and…

Proof of concept for CVE-2024-24590


A Burp Suite extension that integrates OpenAI's GPT to perform an additional passive scan for discovering highly bespoke vulnerabilities and enables…

A tool that checks if a TorchServe instance is vulnerable to CVE-2023-43654