|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|
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.
- 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)
Define risk rating approach for this type of attacks and suggest defence techniques
- Application security professionals
- AI professionals
- project documentation file
- paper file https://arxiv.org/abs/1712.05526
Register as participant
To register as participant add
Owasp Top 5 Machine Learning risks to either:
sessionsmetadata field from your participant's page (find your participant page and look for the edit link).
- or the
participantsmetadata field from this git session page
Back to list of all Working Sessions