Laden Evenementen

« Alle Evenementen

  • Dit evenement is voorbij.

Hundred ways your machine learning systems are vulnerable

6 oktober 2020 van 5:00 pm tot 6:00 pm

Hightech Institute
High Tech Institute and Cydrill invite you for a 45 minutes session on Oktober 6 at 17:00 that will give you a thorough overview of how ML applications can be hacked, and what you can do about it.

This webinar is an excerpt from the brand new face to face or online course on machine learning security that High Tech Institute and its partner for software security Cydrill are launching.

In this webinar, security expert Balázs Kiss will teach you:

  • About the cat and mouse game of software security
  • Why machine learning security is important, and why it is difficult
  • About the many ways the bad guys can compromise your ML systems
  • Some real-world attacks on machine learning systems and how to defend against them
  • How Cydrill courses can raise your paranoia to a healthy level and make your machine learning systems more robust and secure

Outline

Introduction

  • What makes machine learning a valuable target?
  • Threats from the real world:
    – Some real-world abuse examples
    – Dealing with AI/ML threats in software security

Machine Learning Security

  • Adversarial ML examples
    – Poisoning and evasion attacks
    – Demo – ML evasion attack
    – Case studies
  • The ML supply chain
    – TensorFlow security issues and vulnerabilities

Learning how not to code

Conclusion, Q&A

Gegevens

Datum:
6 oktober 2020
Tijd:
5:00 pm tot 6:00 pm
Evenement Categorie:
Evenement Tags:
Site:
https://www.hightechinstitute.nl/webinar-ml-security/

Organisator

High Tech Institute
Telefoon:
+31 85 401 3600
E-mail:
training@hightechinstitute.nl
Site:
https://www.hightechinstitute.nl/
Meld je aan voor onze nieuwsbrief

Meld je aan voor onze nieuwsbrief

Ontvang wekelijks een email met daarin de meest interessante industriele vakbeurzen, congressen, seminars en webinars die in de daaropvolgende 2 weken plaats vinden (voorbeeld).

Gelukt! Ter verificatie is zojuist een email naar jou verzonden. Controleer je 'Postvak in' of spam map om je aanmelding te bevestigen!