Explore the concept of cross-domain transferability of adversarial perturbations in this 42-minute lecture from the University of Central Florida. Delve into the paper's contents, covering the introduction, related work, and the Transferable Generative Adversarial Model. Examine key components such as Discriminator Loss and Relativistic Cross-Entropy. Analyze experimental settings and results, including training progress visualization, Gaussian kernel size, and attention shift. Conclude with a discussion of arguments for and against the presented approach, gaining a comprehensive understanding of this advanced topic in adversarial machine learning.
Cross-Domain Transferability of Adversarial Perturbations - CAP6412 Spring 2021
University of Central Florida via YouTube
Overview
Syllabus
Intro
About the paper
Contents
Introduction
Related Work
Transferable Generative Adversarial Model
Discriminator Loss
Relativistic Cross-Entropy
Experimental settings
Experiments
Results: Training progress visualization
Results: Gaussian kernel size
Results: Attention shift
Conclusion
Arguments For
Arguments Against
Taught by
UCF CRCV
