CNN Classifier's Robustness Enhancement when Preserving Privacy

Simple item page
dc.contributor.authorHasnat, Abul
dc.contributor.authorShvai, Nadiya
dc.contributor.authorNakib, Amir
dc.date.accessioned2022-03-29T18:33:30Z
dc.date.available2022-03-29T18:33:30Z
dc.date.issued2021
dc.description.abstractLaws on privacy preservation challenges supervised learning algorithms in industrial applications and could be an obstacle for the artificial intelligence solutions. In the literature, this issue is never discussed for the algorithm’s design. Indeed, algorithms do not behave the same when the input is modified to protect privacy. Particularly, the unmodified data samples predicts with low confidences show high vulnerability to decision changes. To overcome this challenge, we propose a novel solution that enhances classifier’s robustness by particularly addressing the vulnerable samples. It consists of a novel formulation of the learning objective by hybridizing similarity learning, decision margin and intra-class distance. Experimental results and evaluation on a challenging vehicle image dataset exhibit the high effectiveness and potentials of our method for the privacy preserving classification problems.en_US
dc.identifier.citationAbul Hasnat. CNN Classifier's Robustness Enhancement when Preserving Privacy / Hasnat Abul, Nadiya Shvai, Amir Nakib // IEEE International Conference on Image Processing (ICIP). - 2021. - P. 3887-3891. - https://doi.org/10.1109/ICIP42928.2021.9506188en_US
dc.identifier.urihttps://doi.org/10.1109/ICIP42928.2021.9506188
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/22867
dc.language.isoenuk_UA
dc.relation.sourceIEEE International Conference on Image Processing (ICIP)en_US
dc.statusfirst publisheden_US
dc.subjectlaws on privacy preservation challengesen_US
dc.subjectthe artificial intelligence solutionsen_US
dc.subjecthybridizing similarity learningen_US
dc.subjectPrivacyen_US
dc.subjectVehicle Classificationen_US
dc.subjectCNNen_US
dc.subjectconference abstractsen_US
dc.titleCNN Classifier's Robustness Enhancement when Preserving Privacyen_US
dc.typeConference materialsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
CNN_Classifiers_Robustness_Enhancement_when_Preserving_Privacy.pdf
Size:
4.01 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
7.54 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Кафедра математики