When Deep Fool Meets Deep Prior: Adversarial Attack on Super-Resolution Network

MM '18: ACM Multimedia Conference Seoul Republic of Korea October, 2018, pp. 1930-1938, 2018.

Cited by: 4|Bibtex|Views16|DOI:https://doi.org/10.1145/3240508.3240603
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|dl.acm.org

Abstract:

This paper investigates the vulnerability of the deep prior used in deep learning based image restoration. In particular, the image super-resolution, which relies on the strong prior information to regularize the solution space and plays important roles in the image pre-processing for future viewing and analysis, is shown to be vulnerable...More

Code:

Data:

Your rating :
0

 

Tags
Comments