Owasp Top 5 Machine Learning risks

Track: Owasp Projects
When: Fri AM-1
Where: Portland
Organizers Talal Albacha Talal Albacha , Jean-Noël Colin Jean-Noël Colin
Participants Sebastien Deleersnyder Sebastien Deleersnyder , Jim Newman Jim Newman , Lee Tunnicliffe Lee Tunnicliffe , Luis Saiz Luis Saiz , Peter Turczak Peter Turczak
Remote Participants Ashraf Iftekhar Ashraf Iftekhar , Jean-Noël Colin Jean-Noël Colin , KRBard KRBard , Sereysethy Touch Sereysethy Touch

Why

Deep Learning and Machine Learning become vital part of critical systems like self-driving cars, advanced authentication and automated detection of lesions/tumors. However, research shows that such technologies have inherent risks originated from the process of how the models are being learnt or used. In this session we will learn about OWASP project (Top 5 Machine Learning Risks) which tries to identify and document these risks in general, and then we will discuss one case study about specific risk and how to address it.

What

  • Top 5 Machine Learning Risks Project Introduction
    • project team
    • update about current state of document
  • Developing attacks against machine learning models.
    • Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning (Chen et al. 2017)

Outcomes

Define risk rating approach for this type of attacks and suggest defence techniques

Who

  • Application security professionals
  • AI professionals

Working materials

Register as participant

To register as participant add Owasp Top 5 Machine Learning risks to either:

  1. the sessions metadata field from your participant's page (find your participant page and look for the edit link).
  2. or the participants metadata field from this git session page


Back to list of all Working Sessions