Skip to content

This repository serves as a comprehensive resource for integrating machine learning with security operations, offering innovative cybersecurity strategies. It features a mix of practical code examples, insightful research, and valuable resources tailored for advancing AI/ML cyber security practices.

Notifications You must be signed in to change notification settings

Benjamin-KY/MLSecOps

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 

Repository files navigation

Commitment Issues We Keep it Updated

Machine Learning Security Operations aka MLSecOps

MLSecOps Banner

What is MLSecOps?

Welcome to our MLSecOps project. This project focuses on integrating machine learning with security operations to enhance the security of machine learning operations (MLOps). Here, you'll find a mix of code, research papers, training, useful links, and resources dedicated to MLSecOps.

Contributing is always welcome

We welcome contributions! Please read our Contributing Guide for details on our code of conduct, and the process for submitting pull requests to us.

Contact Information

Project Lead: @Benjamin-KY

Project Link: https://github.com/Benjamin-KY/MLSecOps

AI, ML and MLSecOps centric groups and organisations

Group/Org Link
DEFCON AI Village https://aivillage.org/
ML Commons https://mlcommons.org/
Turing Institute Insert Link

Courses to Learn ML, MLSecOps, AI Assurance, AI Ethics etc etc

I will note two labels/metrics before each course name and link. The first is x/5 where x is the required knowledge about ML/AI in order for the content to be useful. x = 1 is the least required, x =5 is the most. The second label is Vendor-Agnostic or Vendor-Centric. Enjoy!

Difficulty Rating Vendor-Agnostic or Vendor-Centric Name of Course Delivery Method Link
1/5 Vendor-Agnostic OpenML Guide - Threshold to the AI Multiverse Multi-modal https://www.openmlguide.org/ai-portal-gun/ai-portal-gun/
1/5 Vendor-Centric (TensorFlow) Basics of machine learning with TensorFlow Multi-modal https://www.tensorflow.org/resources/learn-ml/basics-of-machine-learning
1/5 Vendor-Centric (TensorFlow) Machine Learning Foundations Videos https://youtube.com/playlist?list=PLOU2XLYxmsII9mzQ-Xxug4l2o04JBrkLV&si=U67LkeKb4nMxzFWP
2/5 Vendor-Centric (Google) Data science and machine learning on Cloud AI Platform Multi-modal https://developers.google.com/learn/topics/datascience?hl=en
2/5 Vendor-Centric (TensorFlow) Machine Learning Crash Course with TensorFlow APIs Multi-modal https://developers.google.com/machine-learning/crash-course/ml-intro
4/5 Vendor-Agnostic Neural Networks and Deep Learning Multi-modal http://neuralnetworksanddeeplearning.com/about.html
4/5 Vendor-Centric (Intel) MLOps Professional Training Package Multi-modal https://learning.intel.com/developer/pages/133/mlops-professional

MLSecOps Repos on GitHub

Repo Link
OWASP Machine Learning Security Top 10 Project https://github.com/OWASP/www-project-machine-learning-security-top-10
MLSecOps Reference Repository https://github.com/disesdi/mlsecops_references

MLOps Repos on GitHub

Repo Link
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning https://github.com/EthicalML/awesome-production-machine-learning
Microsoft AutoML toolkit https://github.com/microsoft/nni
Streamlining Energy Consumption Forecasting using MLOps https://github.com/Philippos01/mlops-energy-forecast-thesis
Free MLOps course from DataTalks.Club https://github.com/DataTalksClub/mlops-zoomcamp/tree/main
Machine Learning Ops with GitHub https://mlops.githubapp.com/
Microsoft MLOps https://github.com/microsoft/MLOps
Learn how to design, develop, deploy and iterate on production-grade ML applications https://github.com/GokuMohandas/mlops-course

ML General

Repo Link
Machine Learning Systems Design https://github.com/chiphuyen/machine-learning-systems-design
Label Studio is a multi-type data labeling and annotation tool with standardized output format https://github.com/HumanSignal/label-studio

People of Note

Experts of Interest

This section is dedicated to profiling leading experts and influencers in the field of MLSecOps. Here, you'll find information on key individuals who are making significant contributions to the intersection of machine learning and security operations.

Expert Profiles

Diana Kelley

  • Background: Diana Kelley is the Chief Information Security Officer (CISO) for Protect AI. She also serves on the boards of WiCyS, The Executive Women’s Forum (EWF), InfoSec World, CyberFuture Foundation, TechTarget Security Editorial, and DevNet AI/ML. Diana was Cybersecurity Field CTO for Microsoft, Global Executive Security Advisor at IBM Security, GM at Symantec, VP at Burton Group (now Gartner), a Manager at KPMG, CTO and co-founder of SecurityCurve, and Chief vCISO at SaltCybersecurity.
  • Contributions: True thought leader in the space. Industry focus but has written on MLSecOps and adjacent domains.
  • Links: LinkedIn, Website

Expert Name 2

  • Background: Brief description of their background.
  • Contributions: Key contributions to the field.
  • Links: Profile, Research

Additional Resources

About

This repository serves as a comprehensive resource for integrating machine learning with security operations, offering innovative cybersecurity strategies. It features a mix of practical code examples, insightful research, and valuable resources tailored for advancing AI/ML cyber security practices.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published