The effective segmentation of 3D data is crucial for a wide range of industrial applications, especially for detecting subtle defects in the field of integrated circuits (IC). Ceramic package substrates (CPS), as an important electronic material, are essential in IC packaging owing to their superior physical and chemical properties. However, the complex structure and minor defects of CPS, along with the absence of a publically available dataset, significantly hinder the development of CPS surface defect detection. In this study, we construct a high-quality point cloud dataset for 3D segmentation of surface defects in CPS, i.e., CPS3D-Seg, which has the best point resolution and precision compared to existing 3D industrial datasets. CPS3D-Seg consists of 1300 point cloud samples under 20 product categories, and each sample provides accurate point-level annotations. Meanwhile, we conduct a comprehensive benchmark based on SOTA point cloud segmentation algorithms to validate the effectiveness of CPS3D-Seg. Additionally, we propose a novel 3D segmentation method based on causal inference (CINet), which quantifies potential confounders in point clouds through Structural Refine (SR) and Quality Assessment (QA) Modules. Extensive experiments demonstrate that CINet significantly outperforms existing algorithms in both mIoU and accuracy.

Abstract Illicit website represents a significant challenge on the Internet. Miscreants exploit the inherent flexibility and invisibility of the Internet to promote illicit activities, particularly online gambling and pornography, intending to generate substantial profits. Previous studies have primarily focused on illicit website detection techniques and analyzed illicit activities using passive datasets. However, constrained by the limitations of passive dataset perspectives, the security community lacks a global understanding of illicit website deployment and operational behavior patterns, particularly during the early stages of website activation. In this paper, we conduct an in-depth analysis of the activities of illicit websites through the advantageous lens of newly registered domains (NRDs). The NRD dataset’s key strength is its broad coverage of emerging illicit activities during observation, complementing previous studies. Specifically, we designed and implemented a framework, NRDMiner, for tracking and analyzing illicit activities associated with large-scale NRDs. This framework supports long-term monitoring of vast quantities of domains and enables accurate identification of illicit websites. Over a 133-day period (July 1–Nov 10, 2024), we collected 27,623,326 NRDs across 481 top-level domains (e.g., and ), and identified 910,794 abusive domains. Our analysis highlights several important patterns. First, illicit activity shows a consistent and steady pattern, with an average of 3.3% of NRDs flagged for illicit website. Moreover, 98% of these domains are first-time registrations. Second, 60% of abusive domains are activated on the same day they are registered, indicating mature automated domain abuse techniques. Third, from a global NRD perspective, we observed regional tendencies in illicit activities, like Asia identified as the primary concentration area, with over 70% of illicit website pages being in Asian languages. Furthermore, we analyzed the deployment and operation of illicit websites. Our work provides a large-scale empirical study of the early-stage activities of illicit websites from the perspective of NRDs, offering valuable evidence that contribute to the timely mitigation of illicit activities.

Due to the widespread use of integrated circuits (IC) package substrates, especially ceramic package substrates (CPS), the industry has raised stringent quality evaluation standards. However, defective packaging substrate samples are scarce and there are many types of defects, so it is difficult for existing semantic segmentation methods to obtain accurate and generalized results on the CPS images. In order to solve the above problems, this article proposes an effective few-shot segmentation method, named dynamic cross characterization network (DCCNet), which can segment untrained CPS defect species using only a small number of labeled CPS samples. First, we introduce a cross sets attention mechanism to enhance the interconnection within the category and better distinguish the differences between the categories. Then, the introduction of the DC block dynamically represents the features, enhances the sensitivity of the features, and reduces the disturbance of differences between classes. Finally, we propose a TB block to deal with feature loss and interclass obfuscation during dimensional change. In addition, we propose a new CPS few-shot segmentation dataset CPSAD-FS to evaluate the proposed DCCNet. Through a large number of comparative experiments and ablation experiments, we have clearly evaluated the state-of-the-art performance of our DCCNet on the CPSAD-FS dataset and verified the effectiveness of each block.

Website owner identification aims to link websites to their real-world owners, which is crucial for credibility assessment and information provenance in information retrieval and vital for applications in cybersecurity, Internet governance, and digital regulation. Existing approaches for website owner identification primarily rely on querying infrastructure registration records or analyzing webpage content. However, these methods often fail due to incomplete or outdated registration records and sparse webpage content. We observe that inter-website relationships, derived from shared infrastructure data such as primary domains, IP blocks, and geolocations, can provide valuable but underutilized ownership cues. To exploit this insight, we propose MetaRAG, a meta-path-guided dynamic graph retrieval-augmented generation framework that performs reasoning using large language models over ownership-relevant paths in a website-centric knowledge graph. MetaRAG consists of three components: (1) a knowledge graph construction module that integrates infrastructure data and crawled webpage content into a unified representation; (2) a meta-path-guided dynamic reasoning module that constrains retrieval to ownership-relevant meta-paths and adaptively decides whether to retrieve more information or perform inference based on evidence completeness; and (3) a multi-path evidence refinement module that aggregates and scores retrieved paths to suppress noise and distill high-confidence ownership signals. We evaluate MetaRAG on two constructed real-world datasets, achieving up to 6.82% improvement over strong baselines. The results demonstrate the effectiveness of our approach in combining structured web knowledge with large language model-based reasoning for more accurate website owner identification.

As the core of the modern electronics industry, integrated circuits (IC) involve highly complex design and manufacturing processes, with the design and fabrication of the package substrates particularly impacting the circuit’s performance and reliability. Therefore, defect detection and classification of integrated circuits package substrates (ICPS) are crucial in IC production. Addressing issues such as the scarcity of data and the challenges in data perception for ICPS, we propose a Fine-grained Region Perception Network (FRPNet) to achieve multi-view perception and precise few-shot classification of ICPS. Specifically, FRPNet consists of three modules: the Category-Perceptive Interaction Module, responsible for feature aggregation perception during class simulation changes; the Fine-Grained Region Aggregation Module, which observes the regions of interest from multiple views and ensures intra-class connectivity; and the Localization Refinement Module, which enhances positional information to ensure the stability of features from local to global scales. Additionally, we construct a CPS2D-FSC dataset comprising single-layer and multi-layer ICPS. We conducted extensive experiments in CPS2D-FSC to validate FRPNet, including comparisons with SOTA algorithms and ablation studies, demonstrating the superiority of our algorithm and the effectiveness of each module.

Penetration testing is widely acknowledged as the foremost method for evaluating network security. However, three challenges impede the generation of strategies that align with human expectations. In this article, we present, for the first time, a method based on human feedback to enhance strategy generation. Our approach comprises two components: agent training and decision-making. During agent training, we establish a hierarchical framework to decompose tasks and a knowledge base to offer advice for improving data efficiency. We then impose constraints on the action space to mitigate ineffective exploration. Finally, we train a reward model based on human feedback and fine tune the model guided by this reward model. In decision-making, we process the model output to enhance decision accuracy. We crafted scenarios based on real-world networks, and the results demonstrate the effectiveness of our method in generating penetration testing strategies that align more closely with human intentions.

Recommendation systems have primarily been limited to research on a single dataset compared to natural language processing and computer vision, which have seen tremendous growth in transferable tasks. Existing approaches for recommendation systems need to be more scalable to arbitrary tasks, given that previous research efforts on transferable recommendations have only yielded brief explorations and neglected systematic studies of sequential tasks. In this regard, we propose the interaction subgraph sequential topology-aware network (ISTN), which overcomes this limitation, enabling transferable sequence recommendations. ISTN performs subgraph sampling and node labeling of user interactions, captures the topological features of the user interaction sequences with the sequential topology auto-encoder, and employs the sequential preference decoupling module to decouple user interaction sequences for transferable adaptive granularity modeling of user preferences. ISTN requires no fine-tuning, and its knowledge transfer capability from the training dataset to the new dataset delivers accurate, individualized recommendation results. ISTN outperforms state-of-the-art performance in transferable contexts with only minor performance degradation compared to the traditional baseline, as shown in Yelp, MovieLens, and Foursquare experiments.

Automatic defect detection on the metal surface is a vital task for product inspection in industrial assembly lines or production processes. Owing to miscellaneous patterns of defects, interclass similarity, intraclass difference, and fewer defect samples, achieving accurate and automatic detection remains a big challenge. What is more, since the rising demand for production efficiency, real-time detection is increasingly desirable. This article proposes a semantic prior and extremely efficient dilated convolution network, named SPEED, for pixel-wise detection on the metal surface, which aims to address the aforementioned issues. The architecture of SPEED involves the following: 1) a semantic prior (SP) branch, with shallow layer and prior mapping module to capture low-level details; and 2) an extremely efficient dilation (EED) branch, with lightweight bottleneck to obtain high-level context. Furthermore, an aggregation module is designed to fuse both types of feature representation. Additionally, different level features of bottleneck are fused to improve the segmentation performance. Experimental results on three metal surface defect datasets indicate that the proposed method outperforms the state-of-the-art approaches in terms of the mean intersection of union, model parameters, FLOPs, and FPS. More specifically, SPEED achieves 92.34% mIoU on NEU-Seg, 88.65% mIoU on Severstal Strip Steel, and 63.91% mIoU on MT Defect.

Deep learning-based recommendation systems have made significant strides in recent years. However, the problem of recommendation systems' generalizability has not been solved. After the training phase, most current models can only solve problems on a particular dataset and are not as generalizable as NLP and CV models. Therefore, a large amount of computing power is required to make conventional recommendation models available to different trades. In real-world scenarios, offline retailers often opt out of recommendation algorithms due to a lack of computer capacity, which puts them at a competitive disadvantage. As a result, we propose an Interaction Graph Auto-encoder Network (IGA) based on topology-aware to address the transferable recommendation problem. IGA is composed primarily of the following components: Interaction Feature Subgraph Extraction, Subgraph Node Labeling, Subgraph Interaction Auto-encoder, and Interaction Preference Attention Network. IGA can transfer knowledge from the training dataset to the new dataset without fine-tuning and give users reliable, personalized recommendation results. Experiments on the MovieLens, Douban, LastFM, and Book-Crossing datasets demonstrate that IGA outperforms state-of-the-art approaches in transferable scenarios. Additionally, IGA requires fewer computing power and is highly adaptable across datasets.

The last decade has witnessed the rapid evolution of the Internet structure, one of which is centralization, that is, Internet core infrastructure has been constantly transferred into the hands of a few popular market participants. Researchers are trying to measure centrality and analyze its security impact from the perspective of traffic analysis. But the underlying distribution of service providers is still enveloped in mysterious veils. In order to address this problem and assess the security risk associated with such centralization. Firstly, we performed linear regression on the data of each kind of service provider in the Alexa Top 1M domains to study the current underlying distribution of various services for the first time. The results show that Zipf’s law is universal in various service providers’ market share, which proves that Internet service infrastructures are centralized. Secondly, we explored the security impacts of centralized infrastructures on the Internet. we conducted attack simulations on providers. Results show that intentional attacks on core providers can greatly downgrade the performance of the Internet. To make matters worse, the quantitative analysis of the provider’s infrastructures found that a considerable number of provider’s infrastructures have low diversity. In addition, we proposed an algorithm to calculate the dependencies between different types of service providers and carried out an evaluation of our datasets, and found the tendency for different services to depend on each other. Our results indicate that the Internet is facing huge security challenges, because the centralized infrastructure will impair service redundancy, and at the same time, it will also cause dependence between infrastructures, which in turn strengthens its centralization.