Machine Learning Security (MLSEC)

 

Course Overview

Your machine learning application works as intended, so you are done, right? But did you consider somebody poisoning your model by training it with intentionally malicious samples? Or sending specially-crafted input – indistinguishable from normal input – to your model that will get completely misclassified? Feeding in too large samples – for example, an image of 16Gbs to crash the application? Because that’s what the bad guys will do. And the list is far from complete.

As a machine learning practitioner, you need to be paranoid just as any developer out there. Interest in attacking machine learning solutions is gaining momentum, and therefore protecting against adversarial machine learning is essential. This needs not only awareness, but also specific skills to protect your ML applications. The course helps you gain these skills by introducing cutting edge attacks and protection techniques from the ML domain.

Machine learning is software after all. That’s why in this course we also teach common secure coding skills and discuss security pitfalls of the Python programming language. Both adversarial machine learning and core secure coding topics come with lots of hands on labs and stories from real life, all to provide a strong emotional engagement to security and to substantially improve code hygiene.

So that you are prepared for the forces of the dark side.

So that nothing unexpected happens.

Nothing.

Who should attend

Python developers working on machine learning systems

Prerequisites

General machine learning and Python development

Course Objectives

  • Getting familiar with essential cyber security concepts
  • Learning about various aspects of machine learning security
  • Attacks and defense techniques in adversarial machine learning
  • Identify vulnerabilities and their consequences
  • Learn the security best practices in Python
  • Input validation approaches and principles
  • Managing vulnerabilities in third party components
  • Understanding how cryptography can support appplication security
  • Learning how to use cryptographic APIs correctly in Python
  • Understanding security testing methodology and approaches
  • Getting familiar with common security testing techniques and tools

Course Content

  • Cyber security basics
  • Machine learning security
  • Input validation
  • Security features
  • Time and state
  • Errors
  • Using vulnerable components
  • Cryptography for developers
  • Security testing
  • Wrap up

Price & Delivery methods

Online Training

Duration
4 days

Price
  • 3,000.— €
Classroom Training

Duration
4 days

Price
  • The Netherlands: 3,000.— €
  • Belgium: 3,000.— €

Schedule

Instructor-led Online Training:   This computer icon in the schedule indicates that this date/time will be conducted as Instructor-Led Online Training.
This is a FLEX course, which is delivered both virtually and in the classroom.

English

Time zone: Central European Time (CET)   ±1 hour

Online Training This is a FLEX course. Time zone: Central European Summer Time (CEST)
Online Training Time zone: Central European Summer Time (CEST)
Online Training Time zone: Central European Summer Time (CEST)
Online Training Time zone: Central European Time (CET)
Online Training Time zone: Eastern European Time (EET)
This is a FLEX course, which is delivered both virtually and in the classroom.

Europe

Germany

Munich This is a FLEX course.   Time zone: Europe/Berlin Enroll:
for online training
for classroom training