# Interpretable and Robust AI in EEG Systems: A Survey

arXiv: https://arxiv.org/abs/2304.10755 · HTML: https://mlsanity.com/paper/2304.10755/

## 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 (most cited first, 29 of 29)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [MOABB: Trustworthy algorithm benchmarking for BCIs](https://mlsanity.com/paper/1805.06427/) (2018)
- [TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition](https://mlsanity.com/paper/2104.02935/) (2021)
- [LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface](https://mlsanity.com/paper/2105.02786/) (2021)
- [Multi-channel EEG recordings during a sustained-attention driving task](https://mlsanity.com/paper/1809.06534/) (2018)
- [SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Staging](https://mlsanity.com/paper/2105.13864/) (2021)
- [Self-supervised Autoregressive Domain Adaptation for Time Series Data](https://mlsanity.com/paper/2111.14834/) (2021)
- [Interpretable Deep Neural Networks for Single-Trial EEG Classification](https://mlsanity.com/paper/1604.08201/) (2016)
- [EEG-based Cross-Subject Driver Drowsiness Recognition with an Interpretable Convolutional Neural Network](https://mlsanity.com/paper/2107.09507/) (2021)
- [Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification](https://mlsanity.com/paper/2202.02472/) (2022)
- [On the Vulnerability of CNN Classifiers in EEG-Based BCIs](https://mlsanity.com/paper/1904.01002/) (2019)
- [GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals](https://mlsanity.com/paper/2006.08924/) (2020)
- [EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification](https://mlsanity.com/paper/2101.10932/) (2021)
- [MIN2Net: End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification](https://mlsanity.com/paper/2102.03814/) (2021)
- [Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts](https://mlsanity.com/paper/2209.11233/) (2022)
- [Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellers](https://mlsanity.com/paper/2001.11569/) (2020)
- [Robust learning from corrupted EEG with dynamic spatial filtering](https://mlsanity.com/paper/2105.12916/) (2021)
- [Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs](https://mlsanity.com/paper/1912.01171/) (2019)
- [Interpreting Deep Learning Models for Epileptic Seizure Detection on EEG signals](https://mlsanity.com/paper/2012.11933/) (2020)
- [DAGAM: A Domain Adversarial Graph Attention Model for Subject Independent EEG-Based Emotion Recognition](https://mlsanity.com/paper/2202.12948/) (2022)
- [Improving EEG Decoding via Clustering-based Multi-task Feature Learning](https://mlsanity.com/paper/2012.06813/) (2020)

## Built on by (most cited first, 10 of 10)

- [From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape](https://mlsanity.com/paper/2312.10868/) (2023)
- [Explainable artificial intelligence approaches for brain-computer interfaces: a review and design space](https://mlsanity.com/paper/2312.13033/) (2023)
- [Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models](https://mlsanity.com/paper/2605.17562/) (2026)
- [EEG-based Sleep Staging with Hybrid Attention](https://mlsanity.com/paper/2305.09543/) (2023)
- [EENED: End-to-End Neural Epilepsy Detection based on Convolutional Transformer](https://mlsanity.com/paper/2305.10502/) (2023)
- [SelectiveFinetuning: Enhancing Transfer Learning in Sleep Staging through Selective Domain Alignment](https://mlsanity.com/paper/2501.03764/) (2025)
- [Introducing Multimodal Paradigm for Learning Sleep Staging PSG via General-Purpose Model](https://mlsanity.com/paper/2509.22810/) (2025)
- [Different Algorithms (Might) Uncover Different Patterns: A Brain-Age Prediction Case Study](https://mlsanity.com/paper/2402.09464/) (2024)
- [The Importance of Architecture Choice in Deep Learning for Climate Applications](https://mlsanity.com/paper/2402.13979/) (2024)
- [EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection](https://mlsanity.com/paper/2609.00566/) (2026)

## 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.