SIT: Stochastic Input Transformation to Defend Against Adversarial Attacks on Deep Neural Networks
Amira Guesmi, Ihsen Alouani, Mouna Baklouti, Tarek Frikha, Mohamed Salah Abid · IEEE Design and Test · 2021
To better combat the impact of adversarial samples on deep neural networks, a model-agnostic stochastic input transformation (SIT) preprocessing technique is proposed in this article. The inputs are transformed into a new domain to minimize the impact of the adversarial perturbations.