University of Cambridge > Talks.cam > Churchill CompSci Talks > Adversarial Machine Learning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Adversarial Machine Learning

Download to your calendar using vCal

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:

Note that ex-directory lists are not shown.

Other lists

CTR Seminar Series In-person - SPRI seminar room https://maths-cam-ac-uk.zoom.us/j/92663554742?pwd=a2diWW0xTnExSG00YU1NZ0xDc0F1QT09

Other talks

Christmas Social Evening & Annual General Meeting "That's History. That's Truth. I Seen It Myself": T'tc~tsa (Wailaki) and the Enslavement of California Native Americans. Proteomics: Expression Analysis and Subcellular Localisation Gastroenterology and Acute Medicine What’s my reproduction number? Life history strategies: an interdisciplinary perspective How bubble acoustics can help in three apocalypses
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity