Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Thibault Maho"'
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5de16d82fba0bfa7b51c3a7a283b8a2a
https://doi.org/10.1109/icassp43922.2022.9746293
https://doi.org/10.1109/icassp43922.2022.9746293
Publikováno v:
CVPR
CVPR 2021-Conference on Computer Vision and Pattern Recognition
CVPR 2021-Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtual, France. pp.10430--10439
CVPR 2021-Conference on Computer Vision and Pattern Recognition
CVPR 2021-Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtual, France. pp.10430--10439
Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively close to their originals. Last couple of years have witnessed a striking
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5760306501d54b15158d08e7dded8645
https://doi.org/10.1109/cvpr46437.2021.01029
https://doi.org/10.1109/cvpr46437.2021.01029
Publikováno v:
ICIP 2021-IEEE International Conference on Image Processing
ICIP 2021-IEEE International Conference on Image Processing, Sep 2021, Anchorage, Alaska, United States. pp.1-5, ⟨10.1109/ICIP42928.2021.9506053⟩
ICIP 2021-IEEE International Conference on Image Processing, Sep 2021, Anchorage, Alaska, United States. pp.1-5, ⟨10.1109/ICIP42928.2021.9506053⟩
Many defenses have emerged with the development of adversarial attacks. Models must be objectively evaluated accordingly. This paper systematically tackles this concern by proposing a new parameter-free benchmark we coin RoBIC. RoBIC fairly evaluates
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::738c550393f84f13f555ed54a9b99af5
http://arxiv.org/abs/2102.05368
http://arxiv.org/abs/2102.05368
