Explainable Label-flipping Attacks on Human Emotion Assessment System
This addresses security vulnerabilities in emotion assessment systems for healthcare or human-computer interaction applications, but is incremental as it applies known attack methods to a specific domain.
The paper tackles data poisoning attacks via label-flipping on EEG-based human emotion assessment systems, showing that the attacks are successful across different machine learning models like AdaBoost and Random Forest, with varying resistance levels, and uses explainable AI techniques to interpret these attacks.
This paper's main goal is to provide an attacker's point of view on data poisoning assaults that use label-flipping during the training phase of systems that use electroencephalogram (EEG) signals to evaluate human emotion. To attack different machine learning classifiers such as Adaptive Boosting (AdaBoost) and Random Forest dedicated to the classification of 4 different human emotions using EEG signals, this paper proposes two scenarios of label-flipping methods. The results of the studies show that the proposed data poison attacksm based on label-flipping are successful regardless of the model, but different models show different degrees of resistance to the assaults. In addition, numerous Explainable Artificial Intelligence (XAI) techniques are used to explain the data poison attacks on EEG signal-based human emotion evaluation systems.