Proxy application for ingesting into Azure sentinel from Cortex Data Lake

An open-source AI agent that brings the power of Gemini directly into your terminal.

TRAM is an open-source platform designed to advance research into automating the mapping of cyber threat intelligence reports to MITRE ATT&CK®.

The Enhanced MITRE ATT&CK® Coverage Tracker is an Excel tool for SOCs to measure and improve detection coverage of cyber threats. It simplifies tracking of security readiness against ATT&CK® tactic…

MITRE ATT&CK Based App in Power BI

Pocket Flow: Codebase to Tutorial

Protection against Model Serialization Attacks

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…

Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI

Implement prompt tuning on a GPT-2 small model using PyTorch and fine-tune it on three tasks: summarization, question answering, and machine translation.

Mobile Security Framework (MobSF) is an automated, all-in-one mobile application (Android/iOS/Windows) pen-testing, malware analysis and security assessment framework capable of performing static a…

Official inference framework for 1-bit LLMs

In a rapidly evolving tech landscape, a group of developers harnesses the power of LangChain and LangGraph to create a groundbreaking application that enhances natural language understanding. The s…

Python tool for converting files and office documents to Markdown.

SSHamble: Unexpected Exposures in SSH

A demo Jupyter Notebook showcasing a simple local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

An Improved Langchain RAG Tutorial (v2) with local LLMs, database updates, and testing.

The Docker Bench for Security is a script that checks for dozens of common best-practices around deploying Docker containers in production.

Official electron build of draw.io

A New Tamil Large Language Model (LLM) Based on Llama 2

Prisma Cloud serverless function that can accept webhook and send alerts to syslog, S3, and SQS

The simplest way to run Alpaca (and other LLaMA-based local LLMs) on your own computer

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

Prisma Cloud docs

Azure Security Resources and Notes