Functional brain network (FBN) has been becoming an increasingly important way to model the statistical dependence among neural time courses of brain, and provides effective imaging biomarkers for diagnosis of some neurological or psychological disorders. Currently, Pearson’s Correlation (PC) is the simplest and most widely-used method in constructing FBNs. Despite its advantages in statistical meaning and calculated performance, the PC tends to result in a FBN with dense connections. Therefore, in practice, the PC-based FBN needs to be sparsified by removing weak (potential noisy) connections. However, such a scheme depends on a hard-threshold without enough flexibility. Different from this traditional strategy, in this paper, we propose a new approach for estimating FBNs by remodelling PC as an optimization problem, which provides a way to incorporate biological/physical priors into the FBNs. In particular, we introduce an L1-norm regularizer into the optimization model for obtaining a sparse solution. Compared with the hard-threshold scheme, the proposed framework gives an elegant mathematical formulation for sparsifying PC-based networks. More importantly, it provides a platform to encode other biological/physical priors into the PC-based FBNs. To further illustrate the flexibility of the proposed method, we extend the model to a weighted counterpart for learning both sparse and scale-free networks, and then conduct experiments to identify autism spectrum disorders (ASD) from normal controls (NC) based on the constructed FBNs. Consequently, we achieved an 81.52% classification accuracy which outperforms the baseline and state-of-the-art methods.
31 March 2022 in IEEE Transactions on Dependable and Secure Computing
Based on the Threshold Predicate Encryption (TPE), the biometric authentication scheme PassBio aims to correctly authenticate genuine end-users without leaking their biometric privacy information. However, this paper proposes two impersonation attacks to PassBio by merely sending very few query messages. Specifically, an attacker is able to cheat the authentication server with probability 50% by sending the server a random query, or almost 100% by sending the server a collusion of old genuine queries, without being identified. Moreover, in order to defeat the impersonation attacks, this paper presents a Verifiable Threshold Predicate Encryption (VTPE) scheme which includes three components: (1) a multi-segment TPE for reducing the computational cost and communication overhead significantly; (2) a segment-wise watermarking for defeating the random attacks; and (3) a challenge-response mechanism for defeating the replay and collusion attacks. In addition, the watermarking also creates a secure channel between the querying user and the server. The experiments on both simulated feature vectors and real face images demonstrate that the present attacks and countermeasures are effective and efficient.
26 June 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
This research presents a music theory-inspired acoustic representation (hereafter, MTAR) to address improved speech emotion recognition. The recognition of emotion in speech and music is developed in parallel, yet a relatively limited understanding of MTAR for interpreting speech emotions is involved. In the present study, we use music theory to study representative acoustics associated with emotion in speech from vocal emotion expressions and auditory emotion perception domains. In experiments assessing the role and effectiveness of the proposed representation in classifying discrete emotion categories and predicting continuous emotion dimensions, it shows promising performance compared with extensively used features for emotion recognition based on the spectrogram, Mel-spectrogram, Mel-frequency cepstral coefficients, VGGish, and the large baseline feature sets of the INTERSPEECH challenges. This proposal opens up a novel research avenue in developing a computational acoustic representation of speech emotion via music theory.
Recently, deep neural networks (DNNs) have achieved exciting things in many fields. However, the DNN models have been proven to divulge privacy, so it is imperative to protect the private information of the models. Differential privacy is a promising method to provide privacy protection for DNNs. However, existing DNN models based on differential privacy protection usually inject the same level of noise into parameters, which may lead to a balance between model performance and privacy protection. In this paper, we propose an adaptive differential privacy scheme based on entropy theory for training DNNs, with the aim of giving consideration to the model performance and protecting the private information in the training data. The proposed scheme perturbs the gradients according to the information gain of neurons during training, that is, in the process of back propagation, less noise is added to neurons with larger information gain, and vice-versa. Rigorous experiments conducted on two real datasets demonstrate that the proposed scheme is highly effective and outperforms existing solutions.
Autism spectrum disorder (ASD) is a lifelong neurological disease, which seriously reduces the patients’ life quality. Generally, an early diagnosis is beneficial to improve ASD children’s life quality. Current methods based on samples from multiple sites for ASD diagnosis perform poorly in generalization due to the heterogeneity of the data from multiple sites. To address this problem, this paper presents a similarity measure-based approach for ASD diagnosis. Specifically, the few-shot learning strategy is used to measure potential similarities in the RS-fMRI data distributions, and, furthermore, a similarity function for samples from multiple sites is trained to enhance the generalization. On the ABIDE database, the presented approach is compared to some representative methods, such as SVM and random forest, in terms of accuracy, precision, and F1 score. The experimental results show that the experimental indicators of the proposed method are better than those of the comparison methods to varying degrees. For example, the accuracy on the TRINITY site is more than 5% higher than that of the comparison method, which clearly proves that the presented approach achieves a better generalization performance than the compared methods.