AI Red Teaming ML Frameworks
Tools, frameworks, and resources for adversarial testing of AI systems, offensive security automation, and red team operations using AI. Does NOT include general cybersecurity training, vulnerability scanning, or non-AI-specific penetration testing platforms.
There are 127 ai red teaming frameworks tracked. 1 score above 70 (verified tier). The highest-rated is TalEliyahu/Awesome-AI-Security at 72/100 with 569 stars. 3 of the top 10 are actively maintained.
Get all 127 projects as JSON
curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=ai-red-teaming&limit=20"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
| # | Framework | Score | Tier |
|---|---|---|---|
| 1 |
TalEliyahu/Awesome-AI-Security
Curated resources, research, and tools for securing AI systems |
|
Verified |
| 2 |
The-Art-of-Hacking/h4cker
This repository is maintained by Omar Santos (@santosomar) and includes... |
|
Established |
| 3 |
aw-junaid/Hacking-Tools
This Repository is a collection of different ethical hacking tools and... |
|
Established |
| 4 |
sigstore/model-transparency
Supply chain security for ML |
|
Established |
| 5 |
jiep/offensive-ai-compilation
A curated list of useful resources that cover Offensive AI. |
|
Established |
| 6 |
Kim-Hammar/csle
A research platform to develop automated security policies using... |
|
Established |
| 7 |
sanscript-tech/hacking-tools-scripts
Hacking Scripts that will blow your mind engineered by Hackers ♠️. |
|
Established |
| 8 |
blackhillsinfosec/WifiForge
WifiForge is a tool developed by Black Hills InfoSec to help train... |
|
Established |
| 9 |
brannondorsey/PassGAN
A Deep Learning Approach for Password Guessing (https://arxiv.org/abs/1709.00440) |
|
Established |
| 10 |
McGill-DMaS/Kam1n0-Community
The Kam1n0 Assembly Analysis Platform |
|
Established |
| 11 |
jivoi/awesome-ml-for-cybersecurity
:octocat: Machine Learning for Cyber Security |
|
Established |
| 12 |
evilsocket/pwnagotchi
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning. |
|
Established |
| 13 |
RevEngAI/plugin-ida
RevEng.AI IDA Pro Plugin |
|
Emerging |
| 14 |
arxhr007/Aliens_eye
Hunt down 840+ social media accounts using AI |
|
Emerging |
| 15 |
PadishahIII/RFGuess
基于机器学习的社工字典生成工具. A Machine Learning Approach for Password Guessing. The... |
|
Emerging |
| 16 |
bee-san/Ciphey
⚡ Automatically decrypt encryptions without knowing the key or cipher,... |
|
Emerging |
| 17 |
404notf0und/AI-for-Security-Learning
安全场景、基于AI的安全算法和安全数据分析业界实践 |
|
Emerging |
| 18 |
gsurma/password_cracker
Char-level RNN LSTM password cracker 🔑🔓. |
|
Emerging |
| 19 |
philipperemy/tensorflow-1.4-billion-password-analysis
Deep Learning model to analyze a large corpus of clear text passwords. |
|
Emerging |
| 20 |
CybernetiX-S3C/CybernetiX-S3C.github.io
This is the OFFICIAL CybernetiX S3C website. |
|
Emerging |
| 21 |
Benjamin-KY/MLSecOps
This repository serves as a comprehensive resource for integrating machine... |
|
Emerging |
| 22 |
ThalesGroup/secure-ml
Explore ThalesGroup's comprehensive framework for secure machine learning... |
|
Emerging |
| 23 |
unica-mlsec/mlsec
PhD/MSc course on Machine Learning Security (Univ. Cagliari) |
|
Emerging |
| 24 |
RevEngAI/reait
RevEng.AI Toolkit and Python API |
|
Emerging |
| 25 |
Splinter0/tensorflow-rce
RCE PoC for Tensorflow using a malicious Lambda layer |
|
Emerging |
| 26 |
JosephTLucas/HackThisAI
Adversarial Machine Learning (AML) Capture the Flag (CTF) |
|
Emerging |
| 27 |
greydanus/crypto-rnn
Learning the Enigma with Recurrent Neural Networks |
|
Emerging |
| 28 |
lhmtriet/awesome-vulnerability-assessment
An ever-growing list of resources for data-driven vulnerability assessment... |
|
Emerging |
| 29 |
ashiandd/arsenal-ng
🎯 Launch pentesting commands quickly with arsenal-ng, a modern, streamlined... |
|
Emerging |
| 30 |
incertum/cyber-matrix-ai
Collection of cyber security and "AI" relevant topics |
|
Emerging |
| 31 |
TalEliyahu/awesome-business-of-cybersecurity
Explore cybersecurity’s market dynamics through public companies, capital... |
|
Emerging |
| 32 |
computablefacts/cywise
Cybersecurity for the mortals. |
|
Emerging |
| 33 |
FJRG2007/snatch
📥 AI OSINT - Capture, download, and enjoy. |
|
Emerging |
| 34 |
Billy1900/Awesome-AI-for-cybersecurity
Awesome list of AI for cybersecurity including network (network traffic... |
|
Emerging |
| 35 |
tessera-ops/tessera
42 OWASP security tests for AI models & agents. First framework with... |
|
Emerging |
| 36 |
user1342/Awesome-Binary-Analysis-Automation
A curated list of awesome binary analysis automation training, resources, and tools. |
|
Emerging |
| 37 |
rv427447/Cognitive-Hijacking-in-Long-Context-LLMs
🧠 Explore cognitive hijacking in long-context LLMs, revealing... |
|
Emerging |
| 38 |
numbpill3d/SHEOGORATHS_CHAMPION_ai.JAILBREAK
become SHEOGORATH'S BELOVED CHAMPION In this immersive and delightfully... |
|
Emerging |
| 39 |
tikeswar/kido
White hat hacking passwords using ML |
|
Emerging |
| 40 |
awsm-research/Awesome-AI4DevSecOps
This repository offers a detailed taxonomy of existing AI-driven security... |
|
Emerging |
| 41 |
CODEXISTdev/Project-STROT
Stealthy Tool for Root Oriented Tunneling - a Red Teaming Tool that grabs... |
|
Emerging |
| 42 |
Remarkably-Mind-Blowing-Lab/Awesome-MLSecOps
A reading list for MLSecOps! |
|
Emerging |
| 43 |
anodicpassion/STROT
Stealthy Tool for Root Oriented Tunneling - a Red Teaming Tool that grabs... |
|
Experimental |
| 44 |
vmayoral/ExploitFlow
A library to produce cybersecurity exploitation routes (exploit flows).... |
|
Experimental |
| 45 |
gfranrp/Auto-Pentest-LLM
🔍 Automate penetration testing with an intelligent agent that organizes... |
|
Experimental |
| 46 |
hardware-fab/chameleon
A Dataset for Segmenting and Attacking Obfuscated Power Traces in... |
|
Experimental |
| 47 |
Priyans0830m/IP-INFOGA-SpS
Internet protocol address information gethring Tool |
|
Experimental |
| 48 |
Vignesh010101/red-teaming
A sophisticated red-teaming agent built with LangGraph and Ollama to probe... |
|
Experimental |
| 49 |
nouralmulhem/Cipher-Sphere
🕵️♀️ an implementation of the Dell Hackathon game steganography |
|
Experimental |
| 50 |
Arnoldlarry15/red-set-protocell
An Open-source AI safety platform using dual-agent Sniper/Spotter... |
|
Experimental |
| 51 |
secwexen/aapp-mart
AAPP‑MART is an AI‑driven multi‑agent red team simulation and attack‑path... |
|
Experimental |
| 52 |
AbstractionsLab/c5dec
C5-DEC CAD (part of CyFORT/IPCEI-CIS): AI-enabled toolkit for secure system... |
|
Experimental |
| 53 |
mel4mi/HackGurat
Siber Güvenlik alanında kendini geliştirmek isteyenler için her türlü... |
|
Experimental |
| 54 |
RevEngAI/reai-r2
RevEng.AI Radare2 Plugin |
|
Experimental |
| 55 |
scthornton/securecode-aiml
750-example security training dataset for AI coding assistants covering... |
|
Experimental |
| 56 |
daletoniris/alchemind
From the first artificial neurons to autonomous defense systems — Book +... |
|
Experimental |
| 57 |
sampras343/model-transparency-go
Supply chain security for ML |
|
Experimental |
| 58 |
AI-Security-Research-Group/LLM-Attacks
Comprehensive taxonomy of AI security vulnerabilities, LLM adversarial... |
|
Experimental |
| 59 |
dubermandeer/Worm-GPT-LLM-2026
High-performance C++ execution engine for LLM red-teaming and prompt... |
|
Experimental |
| 60 |
shrey-x/ai-llm-red-team-handbook
🚀 Assess AI/LLM security with this comprehensive toolkit for red team... |
|
Experimental |
| 61 |
HoffmannAlex/Hack-Instagram-Account-with-AI
AI-powered Instagram security hacking tool that uses machine learning to... |
|
Experimental |
| 62 |
shaurya278898/cap-spec
🔍 Establish cryptographic audit trails for AI content systems, ensuring... |
|
Experimental |
| 63 |
Youngsmurk0987-dev/adam-ada
Cyber-security |
|
Experimental |
| 64 |
capetron/ai-security-best-practices
Security guide for deploying AI systems in regulated industries. Covers... |
|
Experimental |
| 65 |
sensible-ki/sensible-ki.github.io
Secure and trustworthy mobile AI. |
|
Experimental |
| 66 |
AI4CYBER-HE/ai4cyber
The main repository of the AI4CYBER Horizon Europe project. Funded by the... |
|
Experimental |
| 67 |
himuxhehe/ai-jail
Isolate AI coding agents using sandbox tools like bwrap and sandbox-exec to... |
|
Experimental |
| 68 |
musthus24/prompt-injection-detection-service
Security middleware for LLM applications that analyzes prompts for injection... |
|
Experimental |
| 69 |
OPBOY1203/redmind
🛠️ Streamline offensive operations with RedMind: a curated collection of... |
|
Experimental |
| 70 |
subham23s/BLOCK-VERIFIER
Blockchain-based ML model and file integrity verification using SHA-256,... |
|
Experimental |
| 71 |
jrajath94/adversarial-prompt-suite
Systematic red-teaming framework for adversarial prompt evaluation —... |
|
Experimental |
| 72 |
alikhan126/loato-bench
LOATO-Bench: Leave-One-Attack-Type-Out evaluation of embedding-based prompt... |
|
Experimental |
| 73 |
NeaByteLab/LLM-Vulnerability
Analysis of LLM Exploitation Through External Data Sources. |
|
Experimental |
| 74 |
vnlinh112/abuse-AI
Containing several tutorials/demo about malicious uses and abuses of... |
|
Experimental |
| 75 |
jaysab1201/SILVERPICK
🚀 Build efficient Position Independent Code for Windows x64 using... |
|
Experimental |
| 76 |
ProgrammerRayyan/auth-cn
🔐 Build authentication UI components easily with Auth CN, designed for... |
|
Experimental |
| 77 |
ZoobyMoo2744/provenance-action
🔒 Fail CI if dependencies in your lockfile lose npm provenance or trusted... |
|
Experimental |
| 78 |
raghavpoonia/ai-security-mastery
Complete 90-day learning path for AI security: ML fundamentals → LLM... |
|
Experimental |
| 79 |
apartresearch/3cb
3cb: Catastrophic Cyber Capabilities Benchmarking of Large Language Models |
|
Experimental |
| 80 |
keusuanl-sec/Ciphey
Automatically decrypt encryptions without knowing the key or cipher, decode... |
|
Experimental |
| 81 |
HoffmannAlex/Pirater-un-compte-GMail-Avec-IA
Outil de recherche et d’apprentissage en sécurité des mots de passe Gmail... |
|
Experimental |
| 82 |
dug22/LockSpot
A machine learning tool designed to analyze ciphertext and identify the most... |
|
Experimental |
| 83 |
satan1a/ai-for-security
对AI相关技术在信息安全领域内进行应用的实践 |
|
Experimental |
| 84 |
michal-kapala/dubRE
ML-driven function symbol extraction plugin for IDA Pro |
|
Experimental |
| 85 |
HoffmannAlex/Hack-Yahoo-Account-with-AI
An AI-driven hacking research and training project focused on Yahoo... |
|
Experimental |
| 86 |
HoffmannAlex/Pirater-un-compte-Yahoo-Avec-IA
Un outil d’IA avancé destiné à l’évaluation et au piratage de la sécurité... |
|
Experimental |
| 87 |
HoffmannAlex/Hack-TikTok-Account-with-AI
An AI-powered educational and research initiative that studies TikTok... |
|
Experimental |
| 88 |
HoffmannAlex/Pirater-un-compte-Facebook-Avec-IA
Outil avancé d’IA conçu pour analyser et pirater la sécurité des comptes... |
|
Experimental |
| 89 |
yadavnikhil17102004/pentest-copilot
Agentic AI-powered exploitation assistant that seamlessly integrates LLMs... |
|
Experimental |
| 90 |
automate-it0/physical-attack-failover-toolkit
A comprehensive toolkit for sysadmins to ensure confident failover execution... |
|
Experimental |
| 91 |
skizap/Advanced-Penetration-Testing-Framework
AI Generated Penetration Testing Framework |
|
Experimental |
| 92 |
Mr-Infect/The_Citadel
The Citadel is not just a training platform; it is a battleground. As AI... |
|
Experimental |
| 93 |
sylvesterkaczmarek/Sylvester-Kaczmarek
Sylvester Kaczmarek's Showcase: Cybersecurity for Space, AI, and Robotics.... |
|
Experimental |
| 94 |
dsp-dr/defcon33-model-security-lab
Security research on AI/ML model vulnerabilities based on DEF CON 33... |
|
Experimental |
| 95 |
amiantos/tyler
Tyler keeps your SillyTavern installation safe from prying eyes |
|
Experimental |
| 96 |
Sherin-SEF-AI/CTF-Term
cross-platform terminal CTF engine with both CLI and TUI interfaces.... |
|
Experimental |
| 97 |
llmbreaker-hq/llmbreaker
Break your AI before hackers do. Red team your LLM APIs in minutes with... |
|
Experimental |
| 98 |
ankitsharma-tech/Ciphey
Automatically decrypt encryptions without knowing the key or cipher, decode... |
|
Experimental |
| 99 |
tessera-ops/awesome-ai-security
A curated list of awesome AI security tools, frameworks, and resources.... |
|
Experimental |
| 100 |
Parisinghchauhan/AuthenTech
AuthenTech employs cutting-edge technology to verify online purchases'... |
|
Experimental |
| 101 |
JosephTLucas/lintML
A security-first linter for code that shouldn't need linting |
|
Experimental |
| 102 |
HoffmannAlex/Hack-WiFi-Password-With-AI
This tool leverages advanced AI techniques to automate the process of... |
|
Experimental |
| 103 |
galpt/dnscrypt-cake
Adjusting CAKE's RTT automatically based on real world network condition... |
|
Experimental |
| 104 |
Bleurayn/VeriAbyss
“VeriAbyss: Unbreakable AI Veracity Oracle fusing AntiSIM v4.0 entropy... |
|
Experimental |
| 105 |
danbyai/danbys-cyber-dojo
🥋 AI-powered Purple Team training framework for CompTIA Security+ prep,... |
|
Experimental |
| 106 |
wutang700/STProcessMonitorBYOVD
🛠 Exploit and control Windows processes using CVE-2025-70795 and... |
|
Experimental |
| 107 |
NikitosHanik4/xianzhi-research
🔐 Extract insights from 5621 security research articles to enhance... |
|
Experimental |
| 108 |
Jhowcae/En0wn
🖥️ Practice Windows privilege escalation techniques with this free,... |
|
Experimental |
| 109 |
Cupcake137/Simula-o_Ataque_PTES_Windows
🔍 Simulate a complete pentest using only native Windows tools, aligning with... |
|
Experimental |
| 110 |
frangelbarrera/Awesome-Hacking-with-AI
The definitive guide to AI-powered offensive security, exploring advanced... |
|
Experimental |
| 111 |
obrunolima1910/CVE-2026-24061
🚨 Exploit CVE-2026-24061, a critical remote authentication bypass in GNU... |
|
Experimental |
| 112 |
omran333-a/Trigon-Legacy
Exploit an integer overflow in iOS 7–9 kernels to gain arbitrary physical... |
|
Experimental |
| 113 |
arnav22098/ac_project
Machine learning cryptanalysis of reduced-round Speck32/64 with neural distinguishers |
|
Experimental |
| 114 |
rauschecker/AI-Hacking-Challenges
A collection of dockerized hacking challenges that focus on breaking out of... |
|
Experimental |
| 115 |
Geoffroeadecorticansaccordionist209/CDEC-B71
Provide secure WiFi credentials and manage access details for CloudBlitz... |
|
Experimental |
| 116 |
Ductai953/CandyHole
🍬 Set up Paqet tunnels easily to bypass internet censorship between Iran and... |
|
Experimental |
| 117 |
CrypToolProject/M209KnownPlaintextAttackML
This project uses Machine Learning (ML), specifically Artificial Neural... |
|
Experimental |
| 118 |
kyegomez/NetNinja
Modular, high-performance, and re-useable building blocks for your hacking... |
|
Experimental |
| 119 |
knooob/Auto-Pentest-LLM
An autonomous AI security agent capable of performing end-to-end penetration... |
|
Experimental |
| 120 |
z-edian/publications
z_edian's cybersecurity policy analyses |
|
Experimental |
| 121 |
101010ai/awesome-attacks-ai
A curated list of modern attacks against Artificial Intelligence |
|
Experimental |
| 122 |
sxz0/awesome-research-venue-guide-ai-cyber
A strategic methodology and curated list of journals, conferences, and... |
|
Experimental |
| 123 |
AryanVBW/AirGhost
AirGhost - WiFi Penetration Testing Platform |
|
Experimental |
| 124 |
PascalCTF/PascalCTF-Beginners-2026
This repository contains all the sourcecodes and writeups of the 2026... |
|
Experimental |
| 125 |
lastenvoy30/Cipher
AI-powered cybersecurity learning platform to analyze threats, practice... |
|
Experimental |
| 126 |
Bassamejlaoui/Jailbreaking-Censored-Aligned-LLMs
Jailbreaking Aligned LLMs with ArtPrompt |
|
Experimental |
| 127 |
GhariebML/ICAIL_Final_Graduation_Project_Random_Password_Maker
🔐 ML-powered password strength analyzer & random password generator using... |
|
Experimental |