Protecting Machine Learning Models from Attacks Training

Infoshare is the largest tech community in CEE and the organizer of the leading tech conference in Gdańsk. It connects startups, investors, corporations, and innovation enthusiasts. It promotes entrepreneurship, knowledge sharing, and networking. Through events, competitions, and programs, it supports the development of the tech ecosystem in Poland and the region.

An advanced, practical course dedicated to key aspects of security in machine learning models. The training combines solid theory with intensive workshops that will allow participants to understand and practically counteract threats in ML environments. Participants will learn to identify, analyze, and effectively protect models against modern attacks, gaining unique skills at the intersection of cybersecurity and artificial intelligence.

• AI engineers and data scientists
• ML solution architects
• Individuals responsible for implementing AI solutions in organizations
• Cybersecurity specialists
• Developers working on advanced model development
• Individuals with basic knowledge of Python, ML libraries (numpy, scikit-learn, tensorflow/pytorch)

• Identification of advanced attack vectors on ML models
• Methods to counteract manipulation of training data
• Practical techniques for securing training and inference processes
• Tools and strategies for protecting sensitive models against cyber threats

• DAY 1: INTRODUCTION TO MLFLOW AND MODEL MANAGEMENT BASICS
   • Basics of MLflow
   • Introduction to MLflow and its architecture
   • Installation and configuration of MLflow

  •  TRACKING EXPERIMENTS WITH MLFLOW TRACKING
     • Logging and tracking ML experiments
     • Managing metadata and results of experiments

  •  MODELING AND STORING MODELS
     • Logging models with MLflow Models
     • Storing models in a model repository
     • Logging and tracking experiments
     • Practical exercises on logging and tracking ML experiments
     • Analysis and interpretation of experiment results

• DAY 2: ADVANCED TECHNIQUES AND PRACTICAL APPLICATIONS
   DEPLOYING MODELS WITH MLFLOW PROJECTS
   • Creating and configuring MLflow projects
   • Deploying models on various platforms

  •  MONITORING MODELS WITH MLFLOW MODELS
     • Monitoring deployed ML models
     • Updating and optimizing deployed models

  •  INTEGRATION WITH OTHER TOOLS AND SERVICES
     • Integrating MLflow with popular ML frameworks (TensorFlow, PyTorch, Scikit-Learn)
     • Integrating MLflow with cloud platforms (AWS, Azure, GCP)

  •  DEPLOYING AND MONITORING THE MODEL
     • Practical exercises on deploying an MLflow model
     • Monitoring and optimizing the deployed model

16 h/2 days