mlsanityData to 14 Oct 2026

Interpretable and Robust AI in EEG Systems: A Survey

arXiv 2304.10755 ↗First posted 21 Apr 2023eess.SP cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

The close coupling of artificial intelligence (AI) and electroencephalography (EEG) has substantially advanced human-computer interaction (HCI) technologies in the AI era. Different from traditional EEG systems, the interpretability and robustness of AI-based EEG systems are becoming particularly crucial. The interpretability clarifies the inner working mechanisms of AI models and thus can gain the trust of users. The robustness reflects the AI's reliability against attacks and perturbations, which is essential for sensitive and fragile EEG signals. Thus the interpretability and robustness of AI in EEG systems have attracted increasing attention, and their research has achieved great progress recently. However, there is still no survey covering recent advances in this field. In this paper, we present the first comprehensive survey and summarize the interpretable and robust AI techniques for EEG systems. Specifically, we first propose a taxonomy of interpretability by characterizing it into three types: backpropagation, perturbation, and inherently interpretable methods. Then we classify the robustness mechanisms into four classes: noise and artifacts, human variability, data acquisition instability, and adversarial attacks. Finally, we identify several critical and unresolved challenges for interpretable and robust AI in EEG systems and further discuss their future directions.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 29 of its 155 references that are in the map. First posted on arXiv 21 Apr 2023.

Builds on

29 of 155 references.

References · 29

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  5. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  6. 2017Dynamic Routing Between Capsulescited by 689
  7. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
  8. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 199
  9. 2017Interpretable Convolutional Neural Networkscited by 162
  10. 2018MOABB: Trustworthy algorithm benchmarking for BCIscited by 82
  11. 2021TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognitioncited by 52
  12. 2021LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interfacecited by 36
17 more
  1. 2018Multi-channel EEG recordings during a sustained-attention driving taskcited by 32
  2. 2021SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Stagingcited by 32
  3. 2021Self-supervised Autoregressive Domain Adaptation for Time Series Datacited by 29
  4. 2016Interpretable Deep Neural Networks for Single-Trial EEG Classificationcited by 24
  5. 2021EEG-based Cross-Subject Driver Drowsiness Recognition with an Interpretable Convolutional Neural Networkcited by 22
  6. 2022Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classificationcited by 21
  7. 2019On the Vulnerability of CNN Classifiers in EEG-Based BCIscited by 17
  8. 2020GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signalscited by 16
  9. 2021EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classificationcited by 16
  10. 2021MIN2Net: End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classificationcited by 16
  11. 2022Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shiftscited by 16
  12. 2020Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellerscited by 15
  13. 2021Robust learning from corrupted EEG with dynamic spatial filteringcited by 14
  14. 2019Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIscited by 13
  15. 2020Interpreting Deep Learning Models for Epileptic Seizure Detection on EEG signalscited by 8
  16. 2022DAGAM: A Domain Adversarial Graph Attention Model for Subject Independent EEG-Based Emotion Recognitioncited by 8
  17. 2020Improving EEG Decoding via Clustering-based Multi-task Feature Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 2; 2026: 2.

10 papers.

  1. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  2. 2023Explainable artificial intelligence approaches for brain-computer interfaces: a review and design spacecited by 5
  3. 2026Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Modelscited by 3
  4. 2023EEG-based Sleep Staging with Hybrid Attentioncited by 1
  5. 2023EENED: End-to-End Neural Epilepsy Detection based on Convolutional Transformercited by 1
  6. 2025SelectiveFinetuning: Enhancing Transfer Learning in Sleep Staging through Selective Domain Alignmentcited by 1
  7. 2025Introducing Multimodal Paradigm for Learning Sleep Staging PSG via General-Purpose Modelcited by 1
  8. 2024Different Algorithms (Might) Uncover Different Patterns: A Brain-Age Prediction Case Studycited by 0
  9. 2024The Importance of Architecture Choice in Deep Learning for Climate Applicationscited by 0
  10. 2026EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selectioncited by 0