The main driving force of the research is the existence of ‘adversarial attacks’. Adversarial attacks rely on the fact that, while imperceptible to the human eye, alterations to input data can result in misclassification, which is a serious security gap in systems based on artificial intelligence.
The more advanced variants of these attacks do not even require detailed knowledge of architecture of the classifier or access to training data, which can result in e-mails with a competitor’s logo being classified as spam by a significant proportion of e-mail boxes. This is a serious obstacle to the spread of intelligent systems. MIM Solutions is responsible for designing, implementing and testing appropriate algorithms in terms of their resistance to data disturbances, in particular to adversarial attacks.