Adversarial Machine Learning

Add to your list(s) Download to your calendar using vCal

• Andrew Coalter, Sidney Sussex College
• Wednesday 30 January 2019, 19:00-19:30
• Wolfson Hall, Churchill College.

If you have a question about this talk, please contact Matthew Ireland.

Machine learning models, including neural networks, have been shown to be vulnerable to malicious inputs designed to compromise their integrity. These adversarial examples manipulate system behaviours in order to cause undesirable outputs.

This talk will discuss this problem, its ramifications, an explantation of how these adversarial examples are generated and an overview of the methods used to try and fight this problem.

This talk is part of the Churchill CompSci Talks series.

This talk is included in these lists:

• Churchill CompSci Talks
• Wolfson Hall, Churchill College
• computer science
• se393's list

Note that ex-directory lists are not shown.