Litcius/Paper detail

SIT: Stochastic Input Transformation to Defend Against Adversarial Attacks on Deep Neural Networks

Amira Guesmi, Ihsen Alouani, Mouna Baklouti, Tarek Frikha, Mohamed Salah Abid

2021IEEE Design and Test20 citationsDOI

Abstract

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.

Topics & Concepts

Adversarial systemPreprocessorTransformation (genetics)Computer scienceDeep neural networksDomain (mathematical analysis)Artificial intelligenceArtificial neural networkTheoretical computer scienceMathematicsChemistryBiochemistryMathematical analysisGeneAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsAdvanced Neural Network Applications