Professor X: Manipulating EEG BCI with Invisible and Robust Backdoor Attack

• URL: http://arxiv.org/abs/2409.20158v1
• Date: Mon, 30 Sep 2024 10:10:52 GMT
• Title: Professor X: Manipulating EEG BCI with Invisible and Robust Backdoor Attack
• Authors: Xuan-Hao Liu, Xinhao Song, Dexuan He, Bao-Liang Lu, Wei-Long Zheng,
• Abstract summary: Professor X is an invisible and robust "mind-controller" that can arbitrarily manipulate the outputs of EEG BCI. Experiments on datasets of three common EEG tasks demonstrate the effectiveness and robustness of Professor X.
• Score: 4.579605201643072
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While electroencephalogram (EEG) based brain-computer interface (BCI) has been widely used for medical diagnosis, health care, and device control, the safety of EEG BCI has long been neglected. In this paper, we propose Professor X, an invisible and robust "mind-controller" that can arbitrarily manipulate the outputs of EEG BCI through backdoor attack, to alert the EEG community of the potential hazard. However, existing EEG attacks mainly focus on single-target class attacks, and they either require engaging the training stage of the target BCI, or fail to maintain high stealthiness. Addressing these limitations, Professor X exploits a three-stage clean label poisoning attack: 1) selecting one trigger for each class; 2) learning optimal injecting EEG electrodes and frequencies strategy with reinforcement learning for each trigger; 3) generating poisoned samples by injecting the corresponding trigger's frequencies into poisoned data for each class by linearly interpolating the spectral amplitude of both data according to previously learned strategies. Experiments on datasets of three common EEG tasks demonstrate the effectiveness and robustness of Professor X, which also easily bypasses existing backdoor defenses.

Related papers

• Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs [20.239554619810935]
  ABAT performs EEG data alignment before adversarial training. Data alignment aligns EEG trials from different domains to reduce their distribution discrepancies. adversarial training further robustifies the classification boundary.
  arXiv  Detail & Related papers  (2024-11-04T13:56:54Z)
• Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder [69.7813498468116]
  We propose Contrastive EEG-Text Masked Autoencoder (CET-MAE), a novel model that orchestrates compound self-supervised learning across and within EEG and text. We also develop a framework called E2T-PTR (EEG-to-Text decoding using Pretrained Transferable Representations) to decode text from EEG sequences.
  arXiv  Detail & Related papers  (2024-02-27T11:45:21Z)
• X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection [113.10386151761682]
  Adversarial attacks targeting texture-free X-ray images are underexplored. In this paper, we take the first step toward the study of adversarial attacks targeted at X-ray prohibited item detection. We propose X-Adv to generate physically printable metals that act as an adversarial agent capable of deceiving X-ray detectors.
  arXiv  Detail & Related papers  (2023-02-19T06:31:17Z)
• Explainable Label-flipping Attacks on Human Emotion Assessment System [4.657100266392171]
  This paper provides an attacker's point of view on data poisoning assaults that use label-flipping. The proposed data poison attacksm based on label-flipping are successful regardless of the model. XAI techniques are used to explain the data poison attacks on EEG signal-based human emotion evaluation systems.
  arXiv  Detail & Related papers  (2023-02-08T15:04:27Z)
• Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces [28.686844131216287]
  Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs) Recent studies have shown that EEG-based BCIs are vulnerable to adversarial attacks, where small perturbations added to the input can cause misclassification. This paper, for the first time, explores adversarial detection in EEG-based BCIs.
  arXiv  Detail & Related papers  (2022-11-28T11:05:32Z)
• Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography [51.45515911920534]
  A task-oriented self-supervised learning approach is proposed to train a more effective anomaly detector. A specific two branch convolutional neural network with larger kernels is designed as the feature extractor. The effectively designed and trained feature extractor has shown to be able to extract better feature representations from EEGs.
  arXiv  Detail & Related papers  (2022-07-04T13:15:08Z)
• High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm [70.50499513259322]
  Current artifact detection pipelines are resource-hungry and rely heavily on hand-crafted features. We propose E4G, a deep learning framework for high frequency EEG artifact detection. Our framework exploits the early exit paradigm, building an implicit ensemble of models capable of capturing uncertainty.
  arXiv  Detail & Related papers  (2021-07-21T07:05:42Z)
• EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks [68.01125081367428]
  Recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is implementable in practice and has never been considered before.
  arXiv  Detail & Related papers  (2020-10-30T20:49:42Z)
• Convolutional Neural Networks for Automatic Detection of Artifacts from Independent Components Represented in Scalp Topographies of EEG Signals [9.088303226909279]
  Artifacts, due to eye movements and blink, muscular/cardiac activity and generic electrical disturbances, have to be recognized and eliminated. ICA is effective to split the signal into independent components (ICs) whose re-projections on 2D scalp topographies (images) allow to recognize/separate artifacts and by UBS. We present a completely automatic and effective framework for EEG artifact recognition by IC topoplots, based on 2D Convolutional Neural Networks (CNNs) Experiments have shown an overall accuracy of above 98%, employing 1.4 sec on a standard PC to classify 32 topoplots
  arXiv  Detail & Related papers  (2020-09-08T12:40:10Z)
• Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellers [45.439697770189134]
  An electroencephalogram (EEG) based brain-computer interface (BCI) speller allows a user to input text to a computer by thought. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable.
  arXiv  Detail & Related papers  (2020-01-30T21:18:46Z)

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.