stacklok/codegate

CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks

Language: Python - Size: 43.7 MB - Last synced at: about 16 hours ago - Pushed at: about 16 hours ago - Stars: 643 - Forks: 76

jamesbower/agentic_shared_memory

This repository contains comprehensive documentation for implementing and optimizing the A-MEM (Associative Memory) system utilizing both vector and graph storage for dynamic memory organization.

Language: Python - Size: 75.2 KB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 0 - Forks: 0

0x6f677548/unicode-injection

Proof of concept demonstrating Unicode injection vulnerabilities using invisible characters to manipulate Large Language Models (LLMs) and AI assistants (e.g., Claude, AI Studio) via hidden prompts or data poisoning. Educational/research purposes only.

Size: 4.49 MB - Last synced at: 10 days ago - Pushed at: 22 days ago - Stars: 1 - Forks: 0

alexdevassy/Machine_Learning_CTF_Challenges

CTF challenges designed and implemented in machine learning applications

Language: HTML - Size: 40.8 MB - Last synced at: 17 days ago - Pushed at: 8 months ago - Stars: 144 - Forks: 26

waterluy/MA2T

✨ Codes for MA2T Adversarial Training.

Language: Python - Size: 2.95 MB - Last synced at: 24 days ago - Pushed at: 24 days ago - Stars: 0 - Forks: 0

hi120ki/openaikeyserver

A server application that generates temporary OpenAI API keys for authorized users through Google OAuth2 authentication

Language: Go - Size: 72.3 KB - Last synced at: 16 days ago - Pushed at: 26 days ago - Stars: 0 - Forks: 1

ShenzheZhu/JailDAM

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model

Size: 3.51 MB - Last synced at: 26 days ago - Pushed at: 26 days ago - Stars: 3 - Forks: 0

wbfoss/mcp-poisoning-poc

This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.

Language: Python - Size: 0 Bytes - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 1 - Forks: 0

JosephTLucas/vger

An interactive CLI application for interacting with authenticated Jupyter instances.

Language: Python - Size: 35.2 MB - Last synced at: 15 days ago - Pushed at: about 1 year ago - Stars: 53 - Forks: 4

mazen160/llmquery

Powerful LLM Query Framework with YAML Prompt Templates. Made for Automation

Language: Python - Size: 243 KB - Last synced at: 13 days ago - Pushed at: 3 months ago - Stars: 20 - Forks: 0

GURPREETKAURJETHRA/LLM-SECURITY

Securing LLM's Against Top 10 OWASP Large Language Model Vulnerabilities 2024

Size: 23.4 MB - Last synced at: about 2 months ago - Pushed at: 12 months ago - Stars: 15 - Forks: 3

plll4zzx/Awesome-LLM-Watermark

A collection list for Large Language Model (LLM) Watermark

Size: 182 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 12 - Forks: 2

balavenkatesh3322/guardrails-demo

LLM Security Project with Llama Guard

Language: Python - Size: 55.7 KB - Last synced at: 22 days ago - Pushed at: about 1 year ago - Stars: 10 - Forks: 0

0PeterAdel/CyberBrain

R1-AI-Training is a repository focused on training AI models to enhance cybersecurity. It provides resources for developing models aimed at addressing challenges like threat detection, anomaly identification, and securing systems, advancing AI-driven solutions for robust cybersecurity.

Language: Python - Size: 15.3 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

bosch-aisecurity-aishield/Reference-Implementations

This repo contains reference implementations, tutorials, samples, and documentation for working with Bosch AIShield

Language: Jupyter Notebook - Size: 167 MB - Last synced at: 20 days ago - Pushed at: 3 months ago - Stars: 10 - Forks: 13

taielab/AISafeNavigator

A Safe and Reliable AI Tools Navigation & Resource Management Platform

Language: TypeScript - Size: 17.9 MB - Last synced at: 3 months ago - Pushed at: 4 months ago - Stars: 4 - Forks: 0

Wapiti08/InsightSecure

demonstrate security practice when deploying a public-facing AI model

Size: 1000 Bytes - Last synced at: 2 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

PromptDefender/PromptDefender-Helper

Prompt Defender helps engineers and security professionals build LLM defences into their applications using a Simple UI, they can take easily advantage of immense LLM security research

Language: Go - Size: 66.6 MB - Last synced at: 5 months ago - Pushed at: 6 months ago - Stars: 1 - Forks: 0

shaialon/ai-security-demos

🤯 AI Security EXPOSED! Live Demos Showing Hidden Risks of 🤖 Agentic AI Flows: 💉Prompt Injection, ☣️ Data Poisoning. Watch the recorded session:

Language: JavaScript - Size: 363 KB - Last synced at: 4 months ago - Pushed at: 10 months ago - Stars: 16 - Forks: 3

StavC/PromptWares

A Jailbroken GenAI Model Can Cause Real Harm: GenAI-powered Applications are Vulnerable to PromptWares

Language: Jupyter Notebook - Size: 469 KB - Last synced at: 4 months ago - Pushed at: 10 months ago - Stars: 6 - Forks: 2

N372unn32/AI-ML-LLM-security-resources

list of resources for AI/ML/LLM security

Size: 19.5 KB - Last synced at: 4 months ago - Pushed at: about 1 year ago - Stars: 1 - Forks: 0

LAiSR-SK/.github

Size: 108 KB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 0 - Forks: 0

wearetyomsmnv/berterpretation

Bert models interpretation and security checker

Language: Python - Size: 40 KB - Last synced at: 2 months ago - Pushed at: 9 months ago - Stars: 0 - Forks: 0

ZySec-AI/.github

ZySec AI: Empowering Security with AI for AI

Size: 126 KB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 0 - Forks: 0

reds-lab/ASSET

This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET achieves state-of-the-art reliability in detecting poisoned samples in end-to-end supervised learning/ self-supervised learning/ transfer learning.

Language: Python - Size: 115 KB - Last synced at: 11 months ago - Pushed at: almost 2 years ago - Stars: 14 - Forks: 0

ngatilio/CertEye

Zero Trust AI 360

Language: CSS - Size: 18.7 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 5 - Forks: 1

AiShieldsOrg/AiShieldsWeb

AiShields is an open-source Artificial Intelligence Data Input and Output Sanitizer

Language: Python - Size: 3.55 MB - Last synced at: about 1 month ago - Pushed at: 11 months ago - Stars: 3 - Forks: 4

ai-risk-armour/Vulnerable-AI-Chatbot

An intentionally vulnerable AI chatbot to learn and practice AI Security.

Language: HTML - Size: 1.94 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0

StavC/ComPromptMized

ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications

Language: Python - Size: 4.93 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 99 - Forks: 9

wwa/FIMjector

FIMjector is an exploit for OpenAI GPT models based on Fill-In-the-Middle (FIM) tokens.

Size: 508 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 2 - Forks: 0

milosilo/RateMyAI

Prompt Engineering Tool for AI Models with cli prompt or api usage

Language: Python - Size: 43.9 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

milosilo/janice

the Janice repository, your hub for exploring machine learning security through practical examples, attack simulations, and defense strategies.

Language: Python - Size: 92.8 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0