# Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks

arXiv: https://arxiv.org/abs/2405.02564 · HTML: https://mlsanity.com/paper/2405.02564/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 74 references that are in the map.
- First posted on arXiv 4 May 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Classification and Geometry of General Perceptual Manifolds](https://mlsanity.com/paper/1710.06487/) (2017)
- [Noisy Activation Functions](https://mlsanity.com/paper/1603.00391/) (2016)
- [Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction](https://mlsanity.com/paper/1911.11616/) (2019)
- [A case for new neural network smoothness constraints](https://mlsanity.com/paper/2012.07969/) (2020)
- [Learning From Brains How to Regularize Machines](https://mlsanity.com/paper/1911.05072/) (2019)
- [TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness](https://mlsanity.com/paper/2104.00671/) (2021)
- [Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations](https://mlsanity.com/paper/2303.03307/) (2023)
- [Towards robust vision by multi-task learning on monkey visual cortex](https://mlsanity.com/paper/2107.14344/) (2021)
- [Interpreting and Evaluating Neural Network Robustness](https://mlsanity.com/paper/1905.04270/) (2019)
- [Top-Down Visual Attention from Analysis by Synthesis](https://mlsanity.com/paper/2303.13043/) (2023)
- [Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception](https://mlsanity.com/paper/2111.06979/) (2021)
- [Adversarial Transfer Attacks With Unknown Data and Class Overlap](https://mlsanity.com/paper/2109.11125/) (2021)

## Built on by (most cited first, 1 of 1)

- [Teaching CORnet Human fMRI Representations for Enhanced Model-Brain Alignment](https://mlsanity.com/paper/2407.10414/) (2024)

## Abstract (arXiv)

Humans effortlessly navigate the dynamic visual world, yet deep neural networks (DNNs), despite excelling at many visual tasks, are surprisingly vulnerable to minor image perturbations. Past theories suggest that human visual robustness arises from a representational space that evolves along the ventral visual stream (VVS) of the brain to increasingly tolerate object transformations. To test whether robustness is supported by such progression as opposed to being confined exclusively to specialized higher-order regions, we trained DNNs to align their representations with human neural responses from consecutive VVS regions while performing visual tasks. We demonstrate a hierarchical improvement in DNN robustness: alignment to higher-order VVS regions leads to greater improvement. To investigate the mechanism behind such robustness gains, we test a prominent hypothesis that attributes human robustness to the unique geometry of neural category manifolds in the VVS. We first reveal that more desirable manifold properties, specifically, smaller extent and better linear separability, indeed emerge across the human VVS. These properties can be inherited by neurally aligned DNNs and predict their subsequent robustness gains. Furthermore, we show that supervision from neural manifolds alone, via manifold guidance, is sufficient to qualitatively reproduce the hierarchical robustness improvements. Together, these results highlight the critical role of the evolving representational space across VVS in achieving robust visual inference, in part through the formation of more linearly separable category manifolds, which may in turn be leveraged to develop more robust AI systems.