Machine Learning Engineer
Berlin, Germany
Security in Machine Learning Engineering: Adversarial attacks and countermeasures
View
Flavio Clesio is a Machine Learning Engineer (NLP, CV, Marketplace RecSys) and at the moment works at MyHammer AG, where he helps build Core Machine Learning applications to exploit revenue opportunities and automation in decision making.
Prior to MyHammer, Flavio was a Data Intelligence lead in the mobile industry, and business intelligence analyst in financial markets, specifically in Non-Performing Loans. He holds a master’s degree in computational intelligence applied in financial markets (exotic credit derivatives).
-
Security in Machine Learning Engineering: Adversarial attacks and countermeasures
Description
Machine Learning algorithms are shaping several industries and playing a main role in production systems in several businesses. However one discussion that receives less attention it’s related to vulnerabilities and attack surfaces in those ML Algorithms. As we have some security frameworks being developed this talk will focus on the attack surfaces of those models and some countermeasures to reduce the exposure of the attack surface. A demo using some known vulnerability of Scikit-Learn regarding white-box attacks will be provided.
This talk will discuss some adversarial attacks, their risks and chain of consequences and some simple countermeasures to avoid those attacks.