Speech recognition systems driven by Deep Neural Networks (DNNs) have revolutionized human-computer interaction through voice interfaces, which significantly facilitate our daily lives. However, the growing popularity of these systems also raises special concerns on their security, particularly regarding backdoor attacks. A backdoor attack inserts one or more hidden backdoors into a DNN model during its training process, such that it does not affect the model’s performance on benign inputs, but forces the model to produce an adversary-desired output if a specific trigger is present in the model input. Despite the initial success of current audio backdoor attacks, they suffer from the following limitations: (i) Most of them require sufficient knowledge, which limits their widespread adoption. (ii) They are not stealthy enough, thus easy to be detected by humans. (iii) Most of them cannot attack live speech, reducing their practicality. To address these problems, in this paper, we propose FlowMur, a stealthy and practical audio backdoor attack that can be launched with limited knowledge. FlowMur constructs an auxiliary dataset and a surrogate model to augment adversary knowledge. To achieve dynamicity, it formulates trigger generation as an optimization problem and optimizes the trigger over different attachment positions. To enhance stealthiness, we propose an adaptive data poisoning method according to Signal-to-Noise Ratio (SNR). Furthermore, ambient noise is incorporated into the process of trigger generation and data poisoning to make FlowMur robust to ambient noise and improve its practicality. Extensive experiments conducted on two datasets demonstrate that FlowMur achieves high attack performance in both digital and physical settings while remaining resilient to state-of- the-art defenses. In particular, a human study confirms that triggers generated by FlowMur are not easily detected by participants. The source code of FlowMur is publicly available at https://github.com/cristinalan/FlowMur.

Trust evaluation assesses trust relationships between entities and facilitates decision-making. Machine Learning (ML) shows great potential for trust evaluation owing to its learning capabilities. In recent years, Graph Neural Networks (GNNs), as a new ML paradigm, have demonstrated superiority in dealing with graph data. This has motivated researchers to explore their use in trust evaluation, as trust relationships among entities can be modeled as a graph. However, current trust evaluation methods that employ GNNs fail to fully satisfy the dynamic nature of trust, overlook the adverse effects of trust-related attacks, and cannot provide convincing explanations on evaluation results. To address these problems, we propose TrustGuard, a GNN-based accurate trust evaluation model that supports trust dynamicity, is robust against typical attacks, and provides explanations through visualization. Specifically, TrustGuard is designed with a layered architecture that contains a snapshot input layer, a spatial aggregation layer, a temporal aggregation layer, and a prediction layer. Among them, the spatial aggregation layer adopts a defense mechanism to robustly aggregate local trust, and the temporal aggregation layer applies an attention mechanism for effective learning of temporal patterns. Extensive experiments on two real-world datasets show that TrustGuard outperforms state-of-the-art GNN-based trust evaluation models with respect to trust prediction across single-timeslot and multi-timeslot, even in the presence of attacks. In addition, TrustGuard can explain its evaluation results by visualizing both spatial and temporal views.

Internet of Things (IoT) aims to create a vast network with billions of things that can seamlessly create and exchange data, establishing intelligent interactions between people and objects around them. It is characterized with openness, heterogeneity, and dynamicity, which inevitably introduce severe security, privacy, and trust issues that hinder the widespread application of IoT. Trust management (TM) holds great promise in identifying malicious nodes, maintaining trust relationships, and enhancing system security. Traditional TM systems (TMSs) can be classified into centralized, semi-centralized, and distributed ones, all three of which suffer from critical challenges and thus are not sufficient for facilitating IoT development. Blockchain, as a disruptive technology, can help addressing the challenges of TM in IoT, thanks to its advanced features, such as decentralization, consistency, and tamper-proofing. As a result, blockchain-based TM (BC-TM) has been extensively studied in recent years to achieve decentralized TM in IoT. However, it still lacks a comprehensive survey on the current state of the arts. To fill this gap, in this article, we conduct a serious survey on BC-TM in IoT. We first propose a set of evaluation criteria that should be met by a TMS in IoT. Then, we propose a taxonomy of TMSs and continue with a thorough review on BC-TM in IoT by employing the proposed criteria. In the end, based on the review, a series of open issues are identified, and future research directions are suggested.

Speaker recognition has become very popular in many application scenarios, such as smart homes and smart assistants, due to ease of use for remote control and economic-friendly features. The rapid development of SRSs is inseparable from the advancement of machine learning, especially neural networks. However, previous work has shown that machine learning models are vulnerable to adversarial attacks in the image domain, which inspired researchers to explore adversarial attacks and defenses in Speaker Recognition Systems (SRS). Unfortunately, existing literature lacks a thorough review of this topic. In this paper, we fill this gap by performing a comprehensive survey on adversarial attacks and defenses in SRSs. We first introduce the basics of SRSs and concepts related to adversarial attacks. Then, we propose two sets of criteria to evaluate the performance of attack methods and defense methods in SRSs, respectively. After that, we provide taxonomies of existing attack methods and defense methods, and further review them by employing our proposed criteria. Finally, based on our review, we find some open issues and further specify a number of future directions to motivate the research of SRSs security.