Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy

TL;DR

This study introduces a biologically inspired hybrid model combining retina gap junctions with deep neural networks to enhance robustness against adversarial noise, analyzing its geometric properties and internal mechanisms.

Contribution

It proposes a novel hybrid model incorporating retina gap junctions, demonstrating improved robustness and revealing how these structures influence the brain manifold's geometry and decision boundaries.

Findings

The hybrid model outperforms other defenses in robustness.

It has a unique 2D decision boundary with high nonlinearity.

G-filter's internal mechanism involves a gradually evolving decision boundary.

Abstract

Deep Neural Networks (DNNs) are vulnerable to elaborately designed adversarial noise, although they have achieved extraordinary success in many tasks. Compared with DNNs, the human visual system is highly robust. However, it is unclear how the human visual system defends against adversarial attacks, especially the role of the early visual system and its influence on the brain manifold. Due to retina gap junctions being crucial for the denoising function in the early visual system, we combine a retina gap junction-based filter, G-filter, with DNN as an abstract human visual system model called the biological hybrid model. We adopt this model to study the defense performance of retina gap junctions and their impact on the brain manifold. Compared with other defense methods, the biological hybrid model is more robust and can be further improved by introducing noise during training. Next, we analyze the manifold and its decision boundary of the biological hybrid model from a geometry perspective. The results show that the biological hybrid model has a unique 2D decision boundary with high nonlinearity and a lower curvature of the decision boundary of the manifold compared to other defense methods. The transforming manifold may account for the high robustness of the biological hybrid model. Finally, to dissect G-filter and clarify its internal mechanism, we borrow the Neural Ordinary Differential Equation (ODE) concept and rewrite G-filter into an equivalent recurrent neural network. The results show that the decision boundary of the model's manifold will gradually change with time and eventually reach a steady state, which is modulated by gap junction conductance, revealing the influence of retina gap junctions on the brain manifold is a gradually evolving process.