Biological networks as defense against adversarial attacks.

In recent years, more and more importance is given to interpretability in the ML field. The best known and most famous area in which the interpretability of a neural network is needed is that of cyber-security. The first paper to expose the potential issue is by Ian Goodfellow et al. 2014, in ”Intriguing properties of neural networks”, in which it is shown how an image, if altered in the right way, can be completely misclassified by a network trained to classify images. In this thesis I proposed a new method based on a hybrid network, i.e half biological and half artificial, in order to develop a neural network capable of resisting a lot of different adversarial attacks. The biological part is based on the hebbian-anti hebbian neural-dynamics, while the artificial one is based on probability and Boltzmann machines."