Reference : How Evolutionary Algorithms and Information Hiding deceive machines and humans for im...
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
Security, Reliability and Trust
http://hdl.handle.net/10993/40853
How Evolutionary Algorithms and Information Hiding deceive machines and humans for image recognition: A research program
English
Bernard, Nicolas mailto [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)]
Leprévost, Franck mailto [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)]
2019
Proceedings of the OLA'2019 International Conference on Optimization and Learning (Bangkok, Thailand, Jan 29-31, 2019)
Theeramunkong, Thanaruk
Bouvry, Pascal mailto
Srichaikul, Piyawut
Springer
Yes
International Conference on Optimization and Learning
from 29-01-2019 to 31-01-2019
[en] Deep Neural Networks are used for a wide range of critical applications, notably for image recognition. The ability to deceive their recognition abilities is an active research domain, since successful deceptions may have disastrous consequences. Still, humans sometimes detect mistakes made by machines when they classify images. One can conceive a system able to solicit humans in case of doubts, namely when humans and machines may disagree. Using Information Hiding techniques, we describe a strategy to construct evolutionary algorithms able to fool both neural networks and humans for image recognition. Although this research is still exploratory, we already describe a concrete fitness function for a specific scenario. Additional scenarii and further research directions are provided.
University of Luxembourg: High Performance Computing - ULHPC
http://hdl.handle.net/10993/40853

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Limited access
synopsis.pdfAuthor preprint189.83 kBRequest a copy

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.