Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG

• URL: http://arxiv.org/abs/2409.03646v1
• Date: Thu, 5 Sep 2024 16:04:57 GMT
• Title: Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG
• Authors: Manshan Guo, Bhavin Choksi, Sari Sadiya, Alessandro T. Gifford, Martina G. Vilas, Radoslaw M. Cichy, Gemma Roig,
• Abstract summary: We trained ResNet50-backbone models on a dual task of classification and EEG prediction. We observed significant correlation between the networks' EEG prediction accuracy, often highest around 100 ms post stimulus onset. We teased apart the data from individual EEG channels and observed strongest contribution from electrodes in the parieto-occipital regions.
• Score: 40.006249083417266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In contrast to human vision, artificial neural networks (ANNs) remain relatively susceptible to adversarial attacks. To address this vulnerability, efforts have been made to transfer inductive bias from human brains to ANNs, often by training the ANN representations to match their biological counterparts. Previous works relied on brain data acquired in rodents or primates using invasive techniques, from specific regions of the brain, under non-natural conditions (anesthetized animals), and with stimulus datasets lacking diversity and naturalness. In this work, we explored whether aligning model representations to human EEG responses to a rich set of real-world images increases robustness to ANNs. Specifically, we trained ResNet50-backbone models on a dual task of classification and EEG prediction; and evaluated their EEG prediction accuracy and robustness to adversarial attacks. We observed significant correlation between the networks' EEG prediction accuracy, often highest around 100 ms post stimulus onset, and their gains in adversarial robustness. Although effect size was limited, effects were consistent across different random initializations and robust for architectural variants. We further teased apart the data from individual EEG channels and observed strongest contribution from electrodes in the parieto-occipital regions. The demonstrated utility of human EEG for such tasks opens up avenues for future efforts that scale to larger datasets under diverse stimuli conditions with the promise of stronger effects.

Related papers

• RISE-iEEG: Robust to Inter-Subject Electrodes Implantation Variability iEEG Classifier [0.0]
  RISE-iEEG stands for Robust Inter-Subject Electrode Implantation Variability iEEG. We developed an iEEG decoder model that can be applied across multiple patients' data without requiring the coordinates of electrode for each patient. Our analysis shows that the performance of RISE-iEEG is 10% higher than that of HTNet and EEGNet in terms of F1 score.
  arXiv  Detail & Related papers  (2024-08-12T18:33:19Z)
• 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)
• Perturbing a Neural Network to Infer Effective Connectivity: Evidence from Synthetic EEG Data [0.7829352305480285]
  We trained neural networks to predict future EEG signals according to historical data and perturbed the networks' input to obtain effective connectivity. CNN and Transformer obtained the best performance on both 3-channel and 90-channel synthetic EEG data, outperforming the classical Granger causality method.
  arXiv  Detail & Related papers  (2023-07-19T06:14:54Z)
• A Neural Active Inference Model of Perceptual-Motor Learning [62.39667564455059]
  The active inference framework (AIF) is a promising new computational framework grounded in contemporary neuroscience. In this study, we test the ability for the AIF to capture the role of anticipation in the visual guidance of action in humans. We present a novel formulation of the prior function that maps a multi-dimensional world-state to a uni-dimensional distribution of free-energy.
  arXiv  Detail & Related papers  (2022-11-16T20:00:38Z)
• Overcoming the Domain Gap in Neural Action Representations [60.47807856873544]
  3D pose data can now be reliably extracted from multi-view video sequences without manual intervention. We propose to use it to guide the encoding of neural action representations together with a set of neural and behavioral augmentations. To reduce the domain gap, during training, we swap neural and behavioral data across animals that seem to be performing similar actions.
  arXiv  Detail & Related papers  (2021-12-02T12:45:46Z)
• Towards Unbiased Visual Emotion Recognition via Causal Intervention [63.74095927462]
  We propose a novel Emotion Recognition Network (IERN) to alleviate the negative effects brought by the dataset bias. A series of designed tests validate the effectiveness of IERN, and experiments on three emotion benchmarks demonstrate that IERN outperforms other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-07-26T10:40:59Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)
• A Novel Transferability Attention Neural Network Model for EEG Emotion Recognition [51.203579838210885]
  We propose a transferable attention neural network (TANN) for EEG emotion recognition. TANN learns the emotional discriminative information by highlighting the transferable EEG brain regions data and samples adaptively. This can be implemented by measuring the outputs of multiple brain-region-level discriminators and one single sample-level discriminator.
  arXiv  Detail & Related papers  (2020-09-21T02:42:30Z)
• Prediction of Human Empathy based on EEG Cortical Asymmetry [0.0]
  lateralization of brain oscillations at specific frequency bands is an important predictor of self-reported empathy scores. Results could be employed in the development of brain-computer interfaces that assist people with difficulties in expressing or recognizing emotions.
  arXiv  Detail & Related papers  (2020-05-06T13:49:56Z)
• Adversarial-based neural networks for affect estimations in the wild [3.3335236123901995]
  In this work, we explore the use of latent features through our proposed adversarial-based networks for recognition in the wild. Specifically, our models operate by aggregating several modalities to our discriminator, which is further conditioned to the extracted latent features by the generator. Our experiments on the recently released SEWA dataset suggest the progressive improvements of our results.
  arXiv  Detail & Related papers  (2020-02-03T16:52:49Z)

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.