# Adversarial Filtering Based Evasion and Backdoor Attacks to EEG-Based Brain-Computer Interfaces

arXiv: https://arxiv.org/abs/2412.07231 · HTML: https://mlsanity.com/paper/2412.07231/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization](https://mlsanity.com/paper/1708.08689/) (2017)
- [Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016](https://mlsanity.com/paper/2004.06286/) (2020)
- [Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class](https://mlsanity.com/paper/2210.09194/) (2022)
- [Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline](https://mlsanity.com/paper/2007.03746/) (2020)
- [Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellers](https://mlsanity.com/paper/2001.11569/) (2020)
- [Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs](https://mlsanity.com/paper/1912.01171/) (2019)
- [EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks](https://mlsanity.com/paper/2011.00101/) (2020)
- [The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing](https://mlsanity.com/paper/2101.03924/) (2021)
- [EEG-Based Driver Drowsiness Estimation Using Feature Weighted Episodic Training](https://mlsanity.com/paper/1909.11456/) (2019)
- [Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review](https://mlsanity.com/paper/2102.02729/) (2021)
- [Spatial Filtering for EEG-Based Regression Problems in Brain-Computer Interface (BCI)](https://mlsanity.com/paper/1702.02914/) (2017)
- [EEG-Based User Reaction Time Estimation Using Riemannian Geometry Features](https://mlsanity.com/paper/1704.08533/) (2017)

## Built on by (most cited first, 3 of 3)

- [SAFE: Secure and Accurate Federated Learning for Privacy-Preserving Brain-Computer Interfaces](https://mlsanity.com/paper/2601.05789/) (2026)
- [BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models](https://mlsanity.com/paper/2602.05401/) (2026)
- [NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces](https://mlsanity.com/paper/2609.08971/) (2026)

## Abstract (arXiv)

A brain-computer interface (BCI) enables direct communication between the brain and an external device. Electroencephalogram (EEG) is a common input signal for BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals, while ignoring their security. Recent studies have shown that machine learning models in BCIs are vulnerable to adversarial attacks. This paper proposes adversarial filtering based evasion and backdoor attacks to EEG-based BCIs, which are very easy to implement. Experiments on three datasets from different BCI paradigms demonstrated the effectiveness of our proposed attack approaches. To our knowledge, this is the first study on adversarial filtering for EEG-based BCIs, raising a new security concern and calling for more attention on the security of BCIs.