Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks

• URL: http://arxiv.org/abs/2605.04443v1
• Date: Wed, 06 May 2026 03:14:06 GMT
• Title: Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks
• Abstract summary: Recent work shows that aligning DCNN representations with human visual cortex activity improves adversarial robustness.<n>One hypothesis suggests that neural alignment confers robustness by biasing models away from brittle high-frequency details and towards the low spatial frequencies (LSF)<n>Here, we investigate whether a spectral bias towards the LSF or the human channel is the primary driver of the adversarial robustness observed in neurally aligned DCNNs.
• Score: 6.784661943290703
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep convolutional neural networks (DCNNs) have rivaled humans on many visual tasks, yet they remain vulnerable to near-imperceptible perturbations generated by adversarial attacks. Recent work shows that aligning DCNN representations with human visual cortex activity improves adversarial robustness, but the mechanisms driving this advantage are unclear. One hypothesis suggests that neural alignment confers robustness by biasing models away from brittle high-frequency details and towards the low spatial frequencies (LSF). However, recent work shows that human object recognition critically depends on a narrow, mid-frequency "human channel". Interestingly, this band was partially preserved in prior LSF-focused studies. Here, we investigate whether a spectral bias towards the LSF or the human channel is the primary driver of the adversarial robustness observed in neurally aligned DCNNs. We first show that DCNNs aligned to higher-order regions of the human ventral visual stream systematically increase reliance on both LSF and the human channel. However, directly steering DCNNs towards these bands revealed a clear dissociation. Biasing models towards the human channel, either alone or together with LSF, does not improve robustness and even impairs it. LSF bias produced some robustness gains, but such improvements are modest despite inducing much larger shifts in spatial-frequency reliance than neurally aligned models. Spatial-frequency-biased models overall show little, if any, increase in similarity to human neural representational geometry. Together, our results suggest that altered spatial-frequency reliance is likely an emergent property of learning more human-like representations rather than the primary mechanism by which neural alignment confers adversarial robustness, and motivate the need for future research examining representational properties beyond spatial-frequency profiles.

Related papers

• Robust Spiking Neural Networks Against Adversarial Attacks [49.08210314590693]
  Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing.<n>In this study, we theoretically demonstrate that threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs.<n>We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances.
  arXiv  Detail & Related papers  (2026-02-24T05:06:12Z)
• Credit Assignment via Neural Manifold Noise Correlation [0.0]
  Credit assignment is central to learning in brains and machines.<n>Noise correlation estimates gradients by correlating perturbations of activity with changes in output.<n>We propose neural manifold noise correlation, which performs credit assignment using perturbations restricted to the neural manifold.
  arXiv  Detail & Related papers  (2026-01-06T01:17:55Z)
• Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation [67.69345363409835]
  Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism.<n>We design Non-Stateful (NS) models progressively removing membrane propagation to its stage-wise role. Experiments reveal a counterintuitive phenomenon: moderate removal in shallow layers improves performance, while excessive removal causes collapse.
  arXiv  Detail & Related papers  (2025-12-05T07:05:53Z)
• Revealing higher-order neural representations of uncertainty with the Noise Estimation through Reinforcement-based Diffusion (NERD) model [0.0]
  We study noise expectation" HORs using neural data from a task which may require the brain to learn about its own noise.<n>We develop and apply a Noise Estimation through Reinforcement-based Diffusion model to characterize how brains may undertake this process.
  arXiv  Detail & Related papers  (2025-03-18T15:08:19Z)
• Understanding the Convergence in Balanced Resonate-and-Fire Neurons [1.4186974630564675]
  Resonate-and-Fire (RF) neurons are an interesting complementary model for integrator neurons in spiking neural networks (SNNs) The recently proposed balanced resonate-and-fire (BRF) neuron marked a significant methodological advance in terms of task performance, spiking and parameter efficiency. This paper aims at providing further intuitions about how and why these convergence advantages emerge.
  arXiv  Detail & Related papers  (2024-06-01T10:04:55Z)
• Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks [18.994287352758697]
  Humans effortlessly navigate the dynamic visual world, yet deep neural networks (DNNs) are surprisingly vulnerable to minor image perturbations.<n>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.<n>We demonstrate a hierarchical improvement in DNN robustness: alignment to higher-order VVS regions leads to greater improvement.
  arXiv  Detail & Related papers  (2024-05-04T04:33:20Z)
• Fixed Inter-Neuron Covariability Induces Adversarial Robustness [26.878913741674058]
  The vulnerability to adversarial perturbations is a major flaw of Deep Neural Networks (DNNs) We have developed the Self-Consistent Activation layer, which comprises of neurons whose activations are consistent with each other, as they conform to a fixed, but learned, covariability pattern. The models with a SCA layer achieved high accuracy, and exhibited significantly greater robustness than multi-layer perceptron models to state-of-the-art Auto-PGD adversarial attacks textitwithout being trained on adversarially perturbed data.
  arXiv  Detail & Related papers  (2023-08-07T23:46:14Z)
• Wavelets Beat Monkeys at Adversarial Robustness [0.8702432681310401]
  We show how physically inspired structures yield new insights into robustness that were previously only thought possible by meticulously mimicking the human cortex. Our work shows how physically inspired structures yield new insights into robustness that were previously only thought possible by meticulously mimicking the human cortex.
  arXiv  Detail & Related papers  (2023-04-19T03:41:30Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Neural Architecture Dilation for Adversarial Robustness [56.18555072877193]
  A shortcoming of convolutional neural networks is that they are vulnerable to adversarial attacks. This paper aims to improve the adversarial robustness of the backbone CNNs that have a satisfactory accuracy. Under a minimal computational overhead, a dilation architecture is expected to be friendly with the standard performance of the backbone CNN.
  arXiv  Detail & Related papers  (2021-08-16T03:58:00Z)
• Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective [78.05383266222285]
  A human imperceptible perturbation can be generated to fool a deep neural network (DNN) for most images. A similar phenomenon has been observed in the deep steganography task, where a decoder network can retrieve a secret image back from a slightly perturbed cover image. We propose two new variants of universal perturbations: (1) Universal Secret Adversarial Perturbation (USAP) that simultaneously achieves attack and hiding; (2) high-pass UAP (HP-UAP) that is less visible to the human eye.
  arXiv  Detail & Related papers  (2021-02-12T12:26:39Z)
• Neural Networks with Recurrent Generative Feedback [61.90658210112138]
  We instantiate this design on convolutional neural networks (CNNs) In the experiments, CNN-F shows considerably improved adversarial robustness over conventional feedforward CNNs on standard benchmarks.
  arXiv  Detail & Related papers  (2020-07-17T19:32:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.