# Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises

arXiv: https://arxiv.org/abs/2206.07282 · HTML: https://mlsanity.com/paper/2206.07282/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 101 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [Adversarial Risk and the Dangers of Evaluating Against Weak Attacks](https://mlsanity.com/paper/1802.05666/) (2018)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [Towards Deep Neural Network Architectures Robust to Adversarial Examples](https://mlsanity.com/paper/1412.5068/) (2014)
- [Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification](https://mlsanity.com/paper/2010.05300/) (2020)
- [Polar Transformer Networks](https://mlsanity.com/paper/1709.01889/) (2017)
- [Adversarial Examples that Fool both Computer Vision and Time-Limited Humans](https://mlsanity.com/paper/1802.08195/) (2018)
- [advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch](https://mlsanity.com/paper/1902.07623/) (2019)
- [Recurrence is required to capture the representational dynamics of the human visual system](https://mlsanity.com/paper/1903.05946/) (2019)
- [Foveation-based Mechanisms Alleviate Adversarial Examples](https://mlsanity.com/paper/1511.06292/) (2015)
- [FOVEA: Foveated Image Magnification for Autonomous Navigation](https://mlsanity.com/paper/2108.12102/) (2021)
- [Biologically Inspired Mechanisms for Adversarial Robustness](https://mlsanity.com/paper/2006.16427/) (2020)
- [FoveaTer: Foveated Transformer for Image Classification](https://mlsanity.com/paper/2105.14173/) (2021)
- [Towards Robust Image Classification Using Sequential Attention Models](https://mlsanity.com/paper/1912.02184/) (2019)
- [Emergent Properties of Foveated Perceptual Systems](https://mlsanity.com/paper/2006.07991/) (2020)
- [Neural Networks with Recurrent Generative Feedback](https://mlsanity.com/paper/2007.09200/) (2020)

## Built on by (most cited first, 4 of 4)

- [A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains](https://mlsanity.com/paper/2310.13849/) (2023)
- [Vision Transformers in Medical Imaging: A Review](https://mlsanity.com/paper/2211.10043/) (2022)
- [Retina gap junctions support the robust perception by warping neural representational geometries along the visual hierarchy](https://mlsanity.com/paper/2604.14200/) (2026)
- [Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers](https://mlsanity.com/paper/2604.20027/) (2026)

## Abstract (arXiv)

Humans actively observe the visual surroundings by focusing on salient objects and ignoring trivial details. However, computer vision models based on convolutional neural networks (CNN) often analyze visual input all at once through a single feed-forward pass. In this study, we designed a dual-stream vision model inspired by the human brain. This model features retina-like input layers and includes two streams: one determining the next point of focus (the fixation), while the other interprets the visuals surrounding the fixation. Trained on image recognition, this model examines an image through a sequence of fixations, each time focusing on different parts, thereby progressively building a representation of the image. We evaluated this model against various benchmarks in terms of object recognition, gaze behavior and adversarial robustness. Our findings suggest that the model can attend and gaze in ways similar to humans without being explicitly trained to mimic human attention, and that the model can enhance robustness against adversarial attacks due to its retinal sampling and recurrent processing. In particular, the model can correct its perceptual errors by taking more glances, setting itself apart from all feed-forward-only models. In conclusion, the interactions of retinal sampling, eye movement, and recurrent dynamics are important to human-like visual exploration and inference.