TY  - JOUR 
AU  - Pialla, Gautier
AU  - Bergmeir, Christoph Norbert
PY  - 2023
UR  - https://hdl.handle.net/10481/85913
AB  - Adversarial attacks represent a threat to every deep neural network. They are particularly effective if they can perturb a given
model while remaining undetectable. They have been initially introduced for image classifiers, and are well studied for...
LA  - eng
PB  - Springer Nature
KW  - Time series
KW  - Adversarial attack
KW  - Smooth perturbations
KW  - InceptionTime
KW  - BIM
TI  - Time series adversarial attacks: an investigation of smooth perturbations and defense approaches
DO  - 10.1007/s41060-023-00438-0
ER  -