Internet measurement research frequently needs to map infrastructure components, such as routers, their physical locations. Although public and commercial geolocation services are often used for this purpose, accuracy when applied network has not been sufficiently assessed. Prior work focused on evaluating the overall of databases, which is dominated by performance end-user IP addresses. In work, we evaluate reliability router in databases. We use a dataset about 1.64M interface addresses...

Unsupervised Deep Learning (DL) techniques have been widely used in various security-related anomaly detection applications, owing to the great promise of being able detect unforeseen threats and superior performance provided by Neural Networks (DNN). However, lack interpretability creates key barriers adoption DL models practice. Unfortunately, existing interpretation approaches are proposed for supervised learning and/or non-security domains, which unadaptable unsupervised fail satisfy...

Host-based threats such as Program Attack, Malware Implantation, and Advanced Persistent Threats (APT), are commonly adopted by modern attackers. Recent studies propose leveraging the rich contextual information in data provenance to detect a host. Data is directed acyclic graph constructed from system audit data. Nodes represent entities (e.g., <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">processes</i>...

Concept drift is one of the most frustrating challenges for learning-based security applications built on closeworld assumption identical distribution between training and deployment.Anomaly detection, important tasks in domains, instead immune to abnormal behavior due without any data (known as zero-positive), which however comes at cost more severe impacts when normality shifts.However, existing studies mainly focus concept behaviour and/or supervised learning, leaving shift zero-positive...

Customer response prediction is critical in many industrial applications such as online advertising and recommendations. In particular, the challenge greater for ride-hailing platforms Uber DiDi, because models need to consider historical real-time event information physical environment, surrounding traffic supply demand conditions. this paper, we propose use dynamically constructed heterogeneous graph each ongoing encode attributes of its surroundings. addition, a multi-layer neural network...

Cloud technology has brought great convenience to enterprises as well customers. System logs record notable events and are becoming valuable resources track investigate system status. Detecting anomaly from fast possible can improve the quality of service significantly. Although many machine learning algorithms (e.g., SVM, Logistic Regression) have high detection accuracy, we find that they assume data clean might training time. Facing these challenges, in this paper, propose Robust Online...

Software Defined Network (SDN) has been widely used in modern network architecture. The SD-WAN is considered as a technology that potential to revolutionize the WAN service usage by utilizing SDN philosophy. Attacking router and controller can affect block entire services. In this paper, we propose machine learning based anomalous traffic detection framework named OADSD over achieve task independent ability of adapting environment. adopts Distributed Dynamic Feature Extraction (DDFE) extract...

Nowadays, various sensors are collecting, storing and transmitting tremendous trajectory data, it is known that raw data seriously wastes the storage, network band computing resource. Line simplification (LS) algorithms an effective approach to attacking this issue by compressing points in a set of continuous line segments, commonly used practice. However, existing LS not sufficient for needs mobile devices. In study, we first develop one-pass error bounded algorithm (OPERB), which scans...

Nowadays e-commerce search has become an integral part of many people's shopping routines. Two critical challenges stay in today's search: how to retrieve items that are semantically relevant but not exact matching query terms, and more personalized different users for the same query. In this paper, we present a novel approach called DPSR, which stands Deep Personalized Semantic Retrieval, tackle problem. Explicitly, share our design decisions on architect retrieval system so as serve...

Performance management in university-based scientific research institutions is essential for driving reform, advancing education quality, and fostering innovation. However, current performance evaluation models often focus solely on indicators, neglecting the critical interdependence between systems. This oversight leads to inefficiencies resource allocation an underestimation of overall institutional performance, particularly universities with varying development levels. To address these...

Copper(I) iodine clusters have drawn intense attention due to their advantageous photophysical properties, such as a high luminescence efficiency, large Stokes shift, and tunable lifetimes. In this work, copper(I) cluster (Cu2I2‐CH3CN) was synthesized, which exhibits unique afterglow emission, ultrahigh quantum yield (90.1% in solid state) aggregation‐induced emission (AIE) behavior. It found that thermally activated delayed fluorescence (TADF) long‐lifetime phosphorescence occur...

Copper(I) iodine clusters have drawn intense attention due to their advantageous photophysical properties, such as a high luminescence efficiency, large Stokes shift, and tunable lifetimes. In this work, copper(I) cluster (Cu2I2‐CH3CN) was synthesized, which exhibits unique afterglow emission, ultrahigh quantum yield (90.1% in solid state) aggregation‐induced emission (AIE) behavior. It found that thermally activated delayed fluorescence (TADF) long‐lifetime phosphorescence occur...

Automated Essay Scoring (AES) plays a crucial role in educational assessment by providing scalable and consistent evaluations of writing tasks. However, traditional AES systems face three major challenges: (1) reliance on handcrafted features that limit generalizability, (2) difficulty capturing fine-grained traits like coherence argumentation, (3) inability to handle multimodal contexts. In the era Multimodal Large Language Models (MLLMs), we propose EssayJudge, first benchmark evaluate...

Sexism affects both women and men, yet research often overlooks misandry suffers from overly broad annotations that limit AI applications. To address this, we introduce BeyondGender, a dataset meticulously annotated according to the latest definitions of misogyny misandry. It features innovative multifaceted labels encompassing aspects sexism, gender, phrasing, misogyny, The includes 6K English 1.7K Chinese sexism instances, alongside 13K non-sexism examples. Our evaluations masked language...

Mobile edge computing is proposed as a promising paradigm to relieve the excessive burden of data centers and mobile networks, which induced by rapid growth Internet Things (IoT). This work introduces cloud-assisted multi-cloudlet framework provision scalable services in cloudlet-based computing. Due constrained computation resources cloudlets limited communication wireless access points (APs), IoT sensors with identical offloading decisions interact each other. To optimize processing delay...

Networks have grown increasingly complicated. Violations of intended policies can compromise network availability and reliability. Network operators need to ensure that their are correctly implemented. This has inspired a research field, verification testing, enables users automatically detect bugs systematically reason network. Furthermore, techniques ranging from formal modeling testing been applied help build reliable systems in electronic design automation software. Inspired by its...

An urban transit system usually consists of several modes, including busses, streetcars, a subway, and light rail. Unfortunately, coordination among different modes remains challenging problem. Difficulties arise when modifying the network structure on strategic level or synchronizing timetables tactical level. Traditional design timetabling intend to solve network-optimization problem based static origin-destination (OD) information, with passenger assignment as subproblem. In this paper,...