Back to Search Start Over

Deterministic versus stochastic dynamical classifiers: opposing random adversarial attacks with noise

Authors :
Chicchi, Lorenzo
Fanelli, Duccio
Febbe, Diego
Buffoni, Lorenzo
Di Patti, Francesca
Giambagli, Lorenzo
Marino, Raffele
Publication Year :
2024

Abstract

The Continuous-Variable Firing Rate (CVFR) model, widely used in neuroscience to describe the intertangled dynamics of excitatory biological neurons, is here trained and tested as a veritable dynamically assisted classifier. To this end the model is supplied with a set of planted attractors which are self-consistently embedded in the inter-nodes coupling matrix, via its spectral decomposition. Learning to classify amounts to sculp the basin of attraction of the imposed equilibria, directing different items towards the corresponding destination target, which reflects the class of respective pertinence. A stochastic variant of the CVFR model is also studied and found to be robust to aversarial random attacks, which corrupt the items to be classified. This remarkable finding is one of the very many surprising effects which arise when noise and dynamical attributes are made to mutually resonate.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2409.13470
Document Type :
Working Paper