Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g., impracticality due to the requirement of white-box information or high control authority, and a lack of stealthiness or effectiveness as they often target all agents or specific fixed agents. To address these issues, we propose AdapAM, a novel framework for adversarial attacks on black-box MAS. AdapAM incorporates two key components: (1) Adaptive Selection Policy simultaneously selects the victim and determines the anticipated malicious action (the action would lead to the worst impact on MAS), balancing effectiveness and stealthiness. (2) Proxy-based Perturbation to Induce Malicious Action utilizes generative adversarial imitation learning to approximate the target MAS, allowing AdapAM to generate perturbed observations using white-box information and thus induce victims to execute malicious action in black-box settings. We evaluate AdapAM across eight multi-agent environments and compare it with four state-of-the-art and commonly-used baselines. Results demonstrate that AdapAM achieves the best attack performance in different perturbation rates. Besides, AdapAM-generated perturbations are the least noisy and hardest to detect, emphasizing the stealthiness.

Large Language Models (LLMs) have emerged as central planners in Vision-and-Language Navigation (VLN), yet their complexity increasingly obscures their internal decision-making. Existing interpretability methods typically isolate temporal criticality from feature salience, creating an alignment gap and failing to account for the behavioral instability of black-box agents. To address this, we propose DEFT, a unified dual-view framework that demystifies agent behavior by jointly analyzing \textit{when} a decision is pivotal and \textit{what} visual evidence grounds it. Featuring a dual-head architecture with a shared latent representation, DEFT employs a \textit{Mask Head} for counterfactual-based criticality detection and an \textit{Action Head} that leverages an ensemble of surrogates to recover robust visual cues. Extensive experiments on MatterPort3D across three LLM-based agents demonstrate that DEFT outperforms baselines in both temporal and feature fidelity. User studies further validate its utility, showing 78% alignment with human intuition.

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the blackboxed agent’s importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent’s importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the masking agents to identify important agents. Specifically, we define the optimization function to minimize the reward difference before and after action randomization and introduce sparsity constraints to encourage the exploration of more action randomization of agents during training. The experimental results in seven multi-agent tasks demonstrate that EMAI achieves higher fidelity in explanations compared to baselines and provides more effective guidance in practical applications concerning understanding policies, launching attacks, and patching policies.

The competitive game between agents exists in many critical applications, such as military unmanned aerial vehicles. It is urgent to test these agents to reduce the significant losses caused by their failures. Existing studies mainly are to construct a testing agent that competes with the target agent to induce its failures. These approaches usually focus on a single task, requiring much more time for multi-task testing. However, if the previously tested tasks (source tasks) and the task to be tested (target task) share similar agents or task objectives, the transferable knowledge in source tasks can potentially increase the effectiveness of testing in the target task. We propose Demo2Test for conducting transfer testing of agents in the competitive environment, i.e., leveraging the demonstrations of failure scenarios from the source task to boost the testing effectiveness in the target task. It trains a testing agent with demonstrations and incorporates the action perturbation at key states to balance the number of revealed failures and their diversity. We conduct experiments in the simulated robotics competitive environments of MuJoCo. The results indicate that Demo2Test outperforms the best-performing baseline with improvements ranging from \(22.38\%\) to \(87.98\%\) , and \(12.69\%\) to \(60.98\%\) , in terms of the number and diversity of discovered failure scenarios, respectively.

In recent years, the signal diagnosis on devices operating under industrial environment has attracted increasing attention. Most data-driven signal diagnosis methods are based on a closed-set assumption that class sets of training and test data are the same. However, in industrial scenarios, during the running process of the device, the operating environment and condition may change over time, continuing generating data belonging to unknown classes with new characteristics and distribution. The unknown classes usually reflect new modes or faults of the device needed to be captured. They are unavailable in training phase, contradicting the closed-set assumption. Existing methods are inappropriate to this type of open-set classification, requiring to classify known classes and recognize unknown classes. To address this challenging problem, this article proposes a generic open-set signal classification method. First, we apply Fourier transform to convert the sensor signals from time domain to frequency domain, then data in the time and frequency domains are fused. Next, a variational encoder-classifier network is proposed to classify known classes and learn the distribution of feature space to extract robust latent features. Finally, based on extreme value theory and entropy, a pair of discriminators determine whether samples belong to unknown or not. The experimental results on two vibration-signal datasets from bearings and nuclear reactor demonstrate the effectiveness and superiority of our proposed open-set signal classification method, especially in practical applications.

In grid-connected inverter systems, the three-phase asymmetric LCL (A-LCL) filter has outstanding characteristics of simple structure, almost the smallest total inductance, and the strong resistance to the adverse effects of parameter shifts. Nevertheless, the order of this kind of power filter is high, and the control model is complicated due to its asymmetric structure. In this paper, a simplified modeling method, which effectively reduces the system order is proposed, without affecting the control performance. Then, the Kalman filter estimation (KF-estimation) is adopted to reconstruct the PCC voltage. A 380 V/50 Hz/6 kW three-phase laboratory setup has been developed to verify the correctness and effectiveness of the proposed control strategy.

To improve the correct detection ratio of existing universal detection methods for image steganography, a new universal steganalysis method based on wavelet package transform (WPT) is presented. Firstly, decompose image into three scales through WPT to obtain 85 coefficient subbands together, and extract the multi-order absolute characteristic function moments of histogram from them as features. And then, normalize these features and combine them to a 255-D feature vector for each image. Lastly, according to this vector, a back-propagation (BP) neural network is designed to classify cover and stego images. A series of experiments validate the performance of proposed method for four kinds of typical steganography of BMP and JPEG images, such as LSB, SS (Spread spectrum), Jsteg and F5 steganography methods. Results show that the proposed method can detect the stego and original images reliably, and the average detection accuracy of our method exceeds those of its closest competitors by at least 7.7% and up to 16.5%.