Enterprise networks face an ever-growing threat from various unknown cyberattacks originating from the Internet. Anomaly-based Network Intrusion Detection Systems (NIDS) have become essential for safeguarding corporate networks, but existing technologies have some limitations in practice. (i) The interweaving of traffic from different service types increases the difficulty of identification. (ii) The scarcity of labeled malicious samples hinders the detection of both known and emerging threats. To tackle these issues, we propose a service-oriented approach to model benign traffic and leverage meta-learning to construct a robust metric space for precise sample comparison. Based on this, we develop SOFA, a two-stage traffic detection framework. In the first stage, SOFA identifies distinct service types within the network and trains independent one-class models for each, ensuring service-specific attack traffic is detected with high precision. The second stage employs a ResNet-based Siamese network to overcome the limitations posed by scarce malicious samples, enhancing detection of both known and emerging attacks. We evaluate SOFA on four widely used network tracing datasets, demonstrating that it achieves state-of-the-art performance and significantly outperforms a diverse set of existing methods in fine-grained attack detection. These results highlight the potential of SOFA for improving network security in a highly dynamic and unbalanced threat environment.

Articulated manipulation represents a nuanced form of trajectory generation, offering a series of service APIs to guide robot arms to understand the structure of articulated objects. The trajectory of the articulated products in the real world is expected to be guided by the complex steps of robotic arms in the metaverse environment. However, the generated joint torque intervals are varied when it comes to applying to different types of robots and appearances of objects. As a result, these intervals exhibit limitations in category-agnostic articulated manipulation. To address these issues, this study proposes a simple articulated manipulation auto-generation method via joint optimization of Vision-Language-Action model (AMAG-JOVLA), which has geometric-centric, category-agnostic, kinematics-aware characteristics. AMAG-JOVLA provides Geometric-Centric Multi-instance Multi-label (GCMIML) representation for articulated manipulation as a multi-instance multi-label problem. Moreover, to generate motion waypoints with fewer spatial, temporal, curvature, and direction errors, a kinematic-aware prompting method, the Geometric Thought Planner (GTP), it is used to build the adaptable manipulation workflows within the inference process of articulated manipulation. GTP also contains a joint optimization mechanism called GTP-Search, which accelerates updating of the label set of GCMIML as a tree-based search problem. The comparative, ablation, and category-agnostic experiments conducted in the metaverse and the real-world environments indicate that the performance of AMAG-JOVLA outperforms that of other comparative methods.

In image captioning, the phenomenon of generating descriptions with missing or non-existent objects is termed hallucination (or object bias). To address this challenge, we propose an Object-aware Prompting strategy (OPCap). Unlike conventional approaches, OPCap enhances semantic understanding through a dual-path feature fusion mechanism. Specifically, an object detector first extracts object tags and their spatial positions from the image, followed by an attribute predictor enriching semantic features of these objects. Structured prompt sequences constructed from these results are processed by a frozen language model and further encoded via QFormer. This information fusion ensures more accurate capture of contextual details during decoding, thereby improving overall comprehension. Experimental results on COCO and Nocaps datasets demonstrate OPCap’s effectiveness in suppressing hallucinations and enhancing caption quality.

Intrusion Detection Systems (IDSs) are vital in detecting network attacks and ensuring the confidentiality and integrity of network resources. Currently, industry-standard IDSs primarily rely on rule-based or anomaly-detection techniques. However, existing detection techniques often generate false positives and negatives, also known as the alert fatigue problem. This influx of incorrect events diminishes the IDS’s efficiency by overburdening security analysts. In this paper, we present ACVS, an innovative automated alert cross-verification system that leverages Graph Neural Networks for identifying misclassifications in security events. Initially, ACVS generates event graphs using attributes like IP addresses and timestamps from sequences of security events and then employs correlation analysis on these events, utilizing alert information to verify misclassifications. Finally, the system uses Graph Neural Networks to classify and correct these security events automatically. We conduct evaluations for ACVS on a substantial real-world dataset comprising over 5 million security events, which are categorized into 5 distinct groups. The results reveal that ACVS markedly enhances the accuracy of intrusion detection systems and substantially reduces the need for manual analysis.

The segmentation of crevasses in remote sensing images plays a pivotal role in diverse domains, including crevasse change monitoring, analysis of ice shelf surface water systems, and investigations into ice shelf stability. In response to the limitations in existing crevasses segmentation methods, which struggle to concurrently capture global structures while preserving local details, this letter introduces CREVNet. CREVNet is designed to achieve precise crevasse segmentation, comprising two integral components: the Transformer Path for enhanced local and global feature extraction, and the Convolutional Path for detailed depiction of crevasses. Evaluation on crevasses dataset, created through the integration of optical remote sensing imagery and laser altimetry data, reveals impressive results. CREVNet achieves F1-score, MIoU, and OA values of 80.40%, 80.98%, and 95.24%, respectively. Notably, CREVNet surpasses the performance of prominent deep learning methods, including Unet, DeepLabV3Plus, DFANet, FPN, MobileViT, and TransUnet. These outcomes underscore CREVNet’s practical potential for effective crevasses segmentation.