Search for: All records

User authentication plays an important role in securing systems and devices by preventing unauthorized accesses. Although surface Electromyogram (sEMG) has been widely applied for human machine interface (HMI) applications, it has only seen a very limited use for user authentication. In this paper, we investigate the use of multi-channel sEMG signals of hand gestures for user authentication. We propose a new deep anomaly detection-based user authentication method which employs sEMG images generated from multi-channel sEMG signals. The deep anomaly detection model classifies the user performing the hand gesture as client or imposter by using sEMG images as the input. Different sEMG image generation methods are studied in this paper. The performance of the proposed method is evaluated with a high-density hand gesture sEMG (HD-sEMG) dataset and a sparse-density hand gesture sEMG (SD-sEMG) dataset under three authentication test scenarios. Among the sEMG image generation methods, root mean square (RMS) map achieves significantly better performance than others. The proposed method with RMS map also greatly outperforms the reference method, especially when using SD-sEMG signals. The results demonstrate the validity of the proposed method with RMS map for user authentication. 

User authentication is an important security mechanism to prevent unauthorized accesses to systems or devices. In this paper, we propose a new user authentication method based on surface electromyogram (sEMG) images of hand gestures and deep anomaly detection. Multi-channel sEMG signals acquired during the user performing a hand gesture are converted into sEMG images which are used as the input of a deep anomaly detection model to classify the user as client or imposter. The performance of different sEMG image generation methods in three authentication test scenarios are investigated by using a public hand gesture sEMG dataset. Our experimental results demonstrate the viability of the proposed method for user authentication. 

Transfer learning using pre-trained deep neural networks (DNNs) has been widely used for plant disease identification recently. However, pre-trained DNNs are susceptible to adversarial attacks which generate adversarial samples causing DNN models to make wrong predictions. Successful adversarial attacks on deep learning (DL)-based plant disease identification systems could result in a significant delay of treatments and huge economic losses. This paper is the first attempt to study adversarial attacks and detection on DL-based plant disease identification. Our results show that adversarial attacks with a small number of perturbations can dramatically degrade the performance of DNN models for plant disease identification. We also find that adversarial attacks can be effectively defended by using adversarial sample detection with an appropriate choice of features. Our work will serve as a basis for developing more robust DNN models for plant disease identification and guiding the defense against adversarial attacks.