University of Cambridge > Talks.cam > Mathematics and Machine Learning > Universal Adversarial Perturbations: Fooling Deep Networks with a Single Image

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹī¸ Information

Universal Adversarial Perturbations: Fooling Deep Networks with a Single Image

Download to your calendar using vCal

If you have a question about this talk, please contact Frank Kelly .

The robustness of classifiers to small perturbations of the data points is a highly desirable property when the classifier is deployed in real and possibly hostile environments. Despite achieving excellent performance on recent visual benchmarks, I will show in this talk that state-of-the-art deep neural networks are highly vulnerable to universal, image-agnostic, perturbations. After demonstrating how such universal perturbations can be constructed, I will analyse the implications of this vulnerability and provide a geometric explanation for the existence of such perturbations via an analysis of the curvature of the decision boundaries.

This talk is part of the Mathematics and Machine Learning series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

FW11, William Gates Building. Zoom link: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon Average on weekdays: 9134.31593794 kWh Room 9, Faculty of Asian & Middle Eastern Studies, Sidgwick Avenue

Other talks

Title tbc Title to be confirmed Online Causal Inference Seminar Title to be confirmed TOWARD AFFORDABLE PREVENTIVE HEALTHCARE: How basic science addresses grand challenges Rothschild Public Lecture: The Quantum Centenary: from Order to Chaos
 

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