no code implementations • 13 Apr 2024 • Munachiso Nwadike, Jialin Li, Hanan Salam
This paper presents our work on an enhanced personalisation strategy, that leverages data augmentation to develop tailored models for continuous valence and arousal prediction.
no code implementations • 30 Dec 2020 • Munachiso Nwadike, Takumi Miyawaki, Esha Sarkar, Michail Maniatakos, Farah Shamout
Extensive evaluation of a state-of-the-art architecture demonstrates that by introducing images with few-pixel perturbations into the training set, an attacker can execute the backdoor successfully without having to be involved with the training procedure.