Adversarial attacks and defenses in deep learning: From a perspective of cybersecurity

S Zhou, C Liu, D Ye, T Zhu, W Zhou, PS Yu - ACM Computing Surveys, 2022 - dl.acm.org
The outstanding performance of deep neural networks has promoted deep learning
applications in a broad set of domains. However, the potential risks caused by adversarial …

Differentiable rendering: A survey

H Kato, D Beker, M Morariu, T Ando… - ar**_Information_ICCV_2021_paper.pdf" data-clk="hl=sv&sa=T&oi=gga&ct=gga&cd=8&d=10140202131392613683&ei=uzW4Z6COCuzDieoPipTCmAU" data-clk-atid="M81QCB08uYwJ" target="_blank">[PDF] thecvf.com

Advdrop: Adversarial attack to dnns by drop** information

R Duan, Y Chen, D Niu, Y Yang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Human can easily recognize visual objects with lost information: even losing most details
with only contour reserved, eg cartoon. However, in terms of visual perception of Deep …

Adversarial examples on object recognition: A comprehensive survey

A Serban, E Poll, J Visser - ACM Computing Surveys (CSUR), 2020 - dl.acm.org
Deep neural networks are at the forefront of machine learning research. However, despite
achieving impressive performance on complex tasks, they can be very sensitive: Small …