Interleaved-Modal Chain-of-Thought (I-MCoT) advances vision-language reasoning, such as Visual Question Answering (VQA).This paradigm integrates specially selected visual evidence from the input image into the context of Vision-Language Models (VLMs), enabling them to ground their reasoning logic in these details.Accordingly, the efficacy of an I-MCoT framework relies on identifying what to see (evidence selection) and when to see it (triggering of insertions).However, existing methods fall short in both aspects.First, for selection, they rely on attention signals, which are unreliable-particularly under severe granularity imbalance between the brief textual query and the informative image.Second, for triggering, they adopt static triggers, which fail to capture the VLMs' dynamic needs for visual evidence.To this end, we propose a novel I-MCoT framework, Active Information-driven Multi-modal Chain-of-Thought (AIM-CoT), which aims to improve both evidence selection and insertion triggering via: (1) Context-enhanced Attention-map Generation (CAG) to mitigate granularity imbalance via textual context enhancement; (2) Active Visual Probing (AVP) to proactively select the most informative evidence via an information foraging process; and (3) Dynamic Attention-shift Trigger (DAT) to precisely activate insertions when VLM's attention shifts from text to visual context.Experiments across three benchmarks and four backbones demonstrate AIM-CoT's consistent superiority.Our code is available at https: //anonymous.4open.science/r/AIMCoT.

The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network (GNN)-based methods primarily prioritize accuracy over diversity, overlooking their inherent tradeoff. To address this, we previously proposed CPGRec, a balance-oriented gaming recommender system. However, CPGRec fails to account for critical disparities in player–game interactions, which carry varying significance in reflecting players’ personal preferences and may exacerbate over-smoothness issues inherent in GNN-based models. Moreover, existing approaches underutilize the reasoning capabilities and extensive knowledge of large language models (LLMs) in addressing these limitations. To bridge this gap, we propose two new modules. First, Preference-informed Edge Reweighting (PER) module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions. Second, Preference-informed Representation Generation (PRG) module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests, thereby refining representations of players and games. Experiments on two Steam datasets demonstrate CPGRec+’s superior accuracy and diversity over state-of-the-art models. The code is accessible at https://github.com/HsipingLi/CPGRec-Plus .

Graph Anomaly Detection (GAD) in heterogeneous networks presents unique challenges due to node and edge heterogeneity. Existing Graph Neural Network (GNN) methods primarily focus on homogeneous GAD and thus fail to address three key issues: (C1) Capturing abnormal signal and rich semantics across diverse meta-paths; (C2) Retaining high-frequency content in HIN dimension alignment; and (C3) Learning effectively from difficult anomaly samples with class imbalance. To overcome these, we propose ChiGAD, a spectral GNN framework based on a novel Chi-Square filter, inspired by the wavelet effectiveness in diverse domains. Specifically, ChiGAD consists of: (1) Multi-Graph Chi-Square Filter, which captures anomalous information via applying dedicated Chi-Square filters to each meta-path graph; (2) Interactive Meta-Graph Convolution, which aligns features while preserving high-frequency information and incorporates heterogeneous messages by a unified Chi-Square Filter; and (3) Contribution-Informed Cross-Entropy Loss, which prioritizes difficult anomalies to address class imbalance. Extensive experiments on public and industrial datasets show that ChiGAD outperforms state-of-the-art models on multiple metrics. Additionally, its homogeneous variant, ChiGNN, excels on seven GAD datasets, validating the effectiveness of Chi-Square filters. Our code is available at https://github.com/HsipingLi/ChiGAD.

Federated Learning (FL) is an emerging distributed learning framework designed to address isolated data island and protect privacy. Besides, Clustered Federated Learning (CFL) is introduced as an efficient multitask scheme to solve heterogeneous problems in FL where clients' data is distributed in non-i.i.d. (non-independent and identically distributed) scenarios. However, due to bandwidth limitation and latency tolerance, the server can only select a subset of clients to participate. Average selection and only selecting low heterogeneous client groups lead to severe results. How to fairly select clients and improve efficient model performance in heterogeneous scenarios with limited communication has become a key issue. We propose a fairness-aware clustered federated learning (FACFL) incentive framework which balances collective and individual fairness. Specifically, our framework models CFL as a bifurcated reverse auction that consists of a first-layer cluster auction and a second-layer client auction. Our framework can dynamically adjust the par-ticipation of clusters and clients according to the communication capabilities. The experimental results on the CIFAR-10 dataset demonstrate that FACFL improves the model performance in severely heterogeneous and communication limited scenarios. Additionally, FACFL can maintain a high level of the training fairness with different numbers of clients.

Automatic modulation classification (AMC) plays an indispensable role in wireless communication systems. Deep learning-based AMC has become the mainstream solution due to its high accuracy and no need for manual feature engineering. However, every coin has two sides. DL-based AMC is susceptible to adversarial perturbations, which are carefully crafted to be superimposed on the transmitted signals in an iteratively try-and-error manner, resulting in incorrect classification. In this paper, we propose a model diversity-based moving target defense mechanism (MD-MTD), which employs multiple classifiers and switches periodically, preventing intelligent attackers from deducing universal adversarial perturbations (UAP). Besides, to jointly optimize the robustness and accuracy of different AMC models to be trained, we design a novel multi-agent reinforcement learning (MARL) module. It is worth mentioning that the proposed algorithm significantly mitigates the curse of dimensionality during the large-scale training process via integrating value-decomposition networks and illegal action masking, improving the feasibility of our solution in real-world wireless communication systems. Experimental results on the GNU radio dataset also exhibit the remarkable advantages of our method in terms of convergence and defense performance.

Intrusion Detection Systems (IDS) are essential tools in network security, which aims to identify malicious traffic to safeguard computers. In recent years, with the application and advancement of machine learning in fields such as image recognition, autonomous driving, and natural language processing (NLP), machine learning-based intrusion detection systems have also rapidly developed. Unfortunately, such IDSs exhibit poor defensive capabilities when facing carefully crafted and imperceptible adversarial attacks. Adversarial attacks manipulate adversarial samples, causing malicious traffic to be misclassified as normal traffic, thereby bypassing intrusion detection systems. Given that adversarial attacks on IDSs in the real world largely operate under the premise of model agnosticism, this paper proposes a black-box attack based on Generative Adversarial Networks (GANs) and active learning. During the iterative training of GANs, the discriminator is covertly constructed as a shadow model of the target IDS, and a generator capable of generating adversarial malicious traffic is trained. Finally, leveraging the transferability of adversarial attacks to DNN, the attack implemented on the shadow model is transferred to the target model, thereby attacking the intrusion detector: Unlike adversarial attacks against image classifiers, adversarial attacks against IDSs must also consider whether the added adversarial perturbations will affect the semantics and functionality of the original malicious traffic. Therefore, the constraint mechanism for modifying feature values is also an important consideration in this paper.

In recent years, the video game industry has experienced substantial growth, presenting players with a vast array of game choices. This surge in options has spurred the need for a specialized recommender system tailored for video games. However, current video game recommendation approaches tend to prioritize accuracy over diversity, potentially leading to unvaried game suggestions. In addition, the existing game recommendation methods commonly lack the ability to establish strict connections between games to enhance accuracy. Furthermore, many existing diversity-focused methods fail to leverage crucial item information, such as item category and popularity during neighbor modeling and message propagation. To address these challenges, we introduce a novel framework, called CPGRec, comprising three modules, namely accuracy-driven, diversity-driven, and comprehensive modules. The first module extends the state-of-the-art accuracy-focused game recommendation method by connecting games in a more stringent manner to enhance recommendation accuracy. The second module connects neighbors with diverse categories within the proposed game graph and harnesses the advantages of popular game nodes to amplify the influence of long-tail games within the player-game bipartite graph, thereby enriching recommendation diversity. The third module combines the above two modules and employs a new negative-sample rating score reweighting method to balance accuracy and diversity. Experimental results on the Steam dataset demonstrate the effectiveness of our proposed method in improving game recommendations. The dataset and source codes are anonymously released at: https://github.com/CPGRec2024/CPGRec.git.