The current paper investigates energy-constraint formation design and analysis problems for multiagent systems with two types of switching interaction topologies; that is, leaderless ones and leader-following ones. Firstly, a new formation control protocol with switching interaction topologies is shown, where the whole energy supply is limited previously. Then, by constructing the relationship of the whole energy supply and the matrix variable, sufficient conditions for leaderless energy-constraint formation design and analysis are respectively presented by the linear matrix inequality tool. Furthermore, an approach is proposed to determine an explicit expression of the formation center function, which determines the macroscopic motion of a multiagent system as a whole and consists of two parts: the initial state term and the formation function term. Moreover, main conclusions of leaderless energy-constraint formation are extended into leader-following multiagent systems by a new two-step transformation approach, where the asymmetric structure feature of leader-following switching interaction topologies is well dealt with. Finally, two numerical examples are provided to demonstrate the effectiveness of main conclusions.

The guaranteed-performance consensualization for high-order linear and nonlinear multiagent systems with switching topologies is respectively realized in a completely distributed manner in the sense that consensus design criteria are independent of interaction topologies and switching motions. This paper first proposes an adaptive consensus protocol with guaranteed-performance constraints and switching topologies, where interaction weights among neighboring agents are adaptively adjusted and state errors among all agents can be regulated. Then, a new translation-adaptive strategy is shown to realize completely distributed guaranteed-performance consensus control and an adaptive guaranteed-performance consensualization criterion is given on the basis of the Riccati inequality. Furthermore, an approach to regulate the consensus control gain and the guaranteed-performance cost is proposed in terms of linear matrix inequalities. Moreover, main conclusions for linear multiagent systems are extended to Lipschitz nonlinear cases. Finally, two numerical examples are provided to demonstrate theoretical results.

Deep neural networks (DNNs) have been widely adopted but they are vulnerable to intentionally crafted adversarial examples. Various attack methods against DNNs have been proposed, yet there still lacks theoretical explanation of adversarial examples. In this paper, we aim to understand adversarial examples from the attacking process and we assume adding perturbations to the key/sensitive regions of the image could fool image classification DNNs. We propose gradient shielding to verify the assumption which ignores insensitive information during generating adversarial examples. Specifically, we propose interactive gradient shielding (IGS) method which selects sensitive regions and then applies gradient-based attack. To remove region selection, we propose adaptive gradient shielding (AGS) method which ignores insensitive gradients automatically. We conduct extensive experiments to evaluate the performance and the results also corroborate our perspective. With this method, we won the first place in IJCAI-AAAC 2019 Non-targeted Adversarial Attack competition.

With the rapid development of information technologies, the security of cyberspace has become increasingly serious. Network intrusion detection is a practical scheme to protect network systems from cyber attacks. However, as new vulnerabilities and unknown attack types are constantly emerging, only a few samples of such attacks can be captured for analysis, which cannot be handled by the existing detection methods deployed in real systems. To handle this problem, we propose a few-shot class-incremental learning method called Branch Fusion Strategy based Network Intrusion Detection (BFS-NID for short), which can continuously learn new attack classes with only a few samples. BFS-NID includes a feature extractor module and a branch classifier learning module. The feature extractor module uses a vision transformer to learn better feature representations in a self-supervised manner, and the parameters of the feature extractor are fixed to avoid catastrophic forgetting when the model learns incrementally. The branch classifier learning module sets re-projection for different branch sessions to enhance the feature representation ability between classes and employs a branch fusion strategy to associate the context of learned attack classes with new classes in different sessions. We conducted extensive experiments on two popular network intrusion detection benchmark datasets (CIC-IDS2017 and CSE-CIC-IDS2018) and the results demonstrate that BFS-NID surpasses the baselines and achieves the best performance.

Speaker recognition is a task that identifies the speaker from multiple audios. Recently, advances in deep learning have considerably boosted the development of speech signal processing techniques. Speaker or speech recognition has been widely adopted in such applications as smart locks, smart vehicle-mounted systems, and financial services. However, deep neural network-based speaker recognition systems (SRSs) are susceptible to adversarial attacks, which fool the system to make wrong decisions by small perturbations, and this has drawn the attention of researchers to the security of SRSs. Unfortunately, there is no systematic review work in this domain. In this work, we conduct a comprehensive survey to fill this gap, which includes the development of SRSs, adversarial attacks and defenses against SRSs. Specifically, we first introduce the mainstream frameworks of SRSs and some commonly used datasets. Then, from the perspectives of adversarial example generation and evaluation, we introduce different attack tasks, the prior knowledge of attacks, perturbation objects, perturbation constraints, and attack effect evaluation indicators. Next, we focus on some effective defense strategies, including adversarial training, attack detection, and input refactoring against existing attacks, and analyze their strengths and weaknesses in terms of fidelity and robustness. Finally, we discuss the challenges posed by audio adversarial examples in SRSs and some valuable research topics in the future.