Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 44 references that are in the map. First posted on arXiv 3 Apr 2026.
Builds on
23 of 44 references.
References · 23
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2014Going Deeper with Convolutionscited by 4,241
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
- 2017Countering Adversarial Images using Input Transformationscited by 520
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
- 2016A study of the effect of JPG compression on adversarial imagescited by 197
- 2018Adversarial Examples that Fool both Computer Vision and Time-Limited Humanscited by 73
11 more
- 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
- 2015Foveation-based Mechanisms Alleviate Adversarial Examplescited by 32
- 2018Humans can decipher adversarial imagescited by 31
- 2017Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developmentscited by 30
- 2020Biologically Inspired Mechanisms for Adversarial Robustnesscited by 29
- 2017Biologically inspired protection of deep networks from adversarial attackscited by 23
- 2020On 1/n neural representation and robustnesscited by 17
- 2017Robustness of classifiers to universal perturbations: a geometric perspectivecited by 15
- 2018Defending against Adversarial Images using Basis Functions Transformationscited by 11
- 2022Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noisescited by 4
- 2018A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retinacited by 1
Built on by
Not cited yet.