检索结果-内蒙古大学图书馆

Consumption-based approaches in proactive detection for content moderation

EPJ DATA SCIENCE 2024年第1期13卷 70页

作者： Elisha, Shahar Pougue-Biyong, John N. Beguerisse-Diaz, Mariano Spotify Ltd London England Univ Oxford Math Inst Oxford England

Implementing effective content moderation systems at scale is an unavoidable and complex challenge facing technology platforms. Developing systems that automate detection and removal of violative content is fraught with performance, safety and fairness considerations that make their implementation challenging. In particular, content-based systems require large amounts of data to train, cannot be easily transferred between contexts, and are susceptible to data drift. For these reasons, platforms employ a wide range of content classification models and rely heavily on human moderation, which can be prohibitively expensive to implement at scale. To address some of these challenges, we developed a framework that relies on consumption patterns to find high-quality leads for human reviewers to assess. This framework leverages consumption networks, and ranks candidate items for review using two techniques: Mean Percentile Ranking (MPR), which we have developed, and an adaptation of Label Propagation (LP). We demonstrate the effectiveness of this approach to find violative material in production settings using professional reviewers, and on a publicly available dataset from MovieLens. We compare our results with a popular collaborative filtering (CF) baseline, and we show that our approach outperforms CF in production settings. Then, we explore how performance can improve using Active Learning techniques. The key advantage of our approach is that it does not require any content-based data;it is able to find both low- and high-consumption items, and is easily scalable and cost effective to run.

关键词： Content moderation proactive detection Consumption networks Label propagation Node ranking Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Covert Multi-Channel Communication Against Interference-Assisted proactive detection

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第9期73卷 14033-14037页

作者： Che, Bohan Shi, Hui Lu, Xingbo Gao, Chang Yang, Weiwei Liu, Jue Jiang, Junhao Army Engn Univ PLA Coll Commun Engn Nanjing 210007 Peoples R China Acad Mil Sci PLA Beijing 100091 Peoples R China Beijing Univ Posts & Telecommun Coll Informat & Commun Engn Beijing 100876 Peoples R China Jinling Inst Technol Sch Network Secur Nanjing 211169 Peoples R China

In this article, covert multi-channel communication against interference-assisted proactive detection is investigated in additive Gaussian white noise (AWGN) channel. We first analyze the detection performance for the warden and derive the covert constraints. Then, to maximize the average effective covert throughput (AECT) of the legitimate communicating parties, we establish an optimization problem by jointly optimizing the sub-channels number and transmit power. Analysis and numerical results show that selecting an appropriate number of sub-channels can improve the AECT against interference-assisted proactive detection comparison with single-channel schemes.

关键词： Interference cancellation Uncertainty Surveillance AWGN channels Throughput Programmable logic arrays Optimization Covert communications proactive detection multi-channel system finite blocklength

来源：评论

学校读者我要写书评

暂无评论

Covert Wireless Communication Against Jamming-Assisted proactive detection

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2023年第8期12卷 1304-1308页

作者： Che, Bohan Shi, Hui Yang, Weiwei Guan, Xinrong Ma, Ruiqian Army Engn Univ PLA Coll Commun Engn Nanjing 210007 Peoples R China

In this letter, we consider the covert wireless communication (CWC) against a jamming-assisted proactive detector in two scenarios corresponding to whether Alice utilizes the jamming to hide the communication signals. Specifically, for the both scenarios, we first obtain Alice's communication strategy by exploiting the statistic channel state information (CSI) of the detecting link. Then, we propose the covertness outage probability (COP) as a new covert communication measure proposed in this letter and derive its closed-form expression which indicates that the lower tolerance value or the longer channel uses are likely to cause communication outage. Numerical results indicate that, against a jamming-assisted proactive detector, hiding the communication signals in the noise is more favorable than exploiting the detector's jamming for achieving covertness, since the latter raises the transmit power at Alice and thus leads to larger COP.

关键词： Covert wireless communication finite block-length proactive detection

来源：评论

学校读者我要写书评

暂无评论

proactive detection of people in need of mental healthcare: accuracy of the community case detection tool among children, adolescents and families in Sri Lanka

引用

CHILD AND ADOLESCENT PSYCHIATRY AND MENTAL HEALTH 2021年第1期15卷 1页

作者： van den Broek, Myrthe Ponniah, Puvaneswary Jeyakumar, P. Judy Ramesh Koppenol-Gonzalez, Gabriela, V Kommu, John Vijay Sagar Kohrt, Brandon A. Jordans, Mark J. D. War Child Holland Res & Dev Amsterdam Netherlands Univ Amsterdam Amsterdam Inst Social Sci Res Amsterdam Netherlands War Child Holland Res & Dev Colombo Sri Lanka Base Hosp Dept Psychiat Valaichchenai Sri Lanka Natl Inst Mental Hlth & Neurosci NIMHANS Dept Child & Adolescent Psychiat Bangalore Karnataka India George Washington Univ Dept Psychiat & Behav Sci Washington DC USA

Background Most children and adolescents in need of mental healthcare remain untreated even when services are available. This study evaluates the accuracy of a new tool, the Community Case detection Tool (CCDT). The CCDT uses illustrated vignettes, two questions and a simple decision algorithm to support proactive community-level detection of children, adolescents and families in need of mental healthcare to improve help-seeking. Methods Trusted and respected community members in the Eastern Province of Sri Lanka used the CCDT in their daily routine. Children and families detected as potentially in need of mental healthcare based on utilizing the CCDT (N = 157, aged 6-18 years) were invited for a clinical interview by a mental health counsellor using the Mini-International Neuropsychiatric Interview for Children and Adolescents (MINI-KID). The CCDT results were compared against the results of the clinical interview. The concurrent validity and performance of the CCDT were also evaluated by comparing the CCDT outcomes against the Strengths and Difficulties Questionnaire (SDQ). Results 7 out of 10 children and families detected by community members using the CCDT were confirmed to be in need for treatment (positive predictive value [PPV] = 0.69;0.75 when compared to the SDQ). detections based on the family problem vignette were most accurate (PPV = 0.76), followed by the internalising problem vignette (PPV = 0.71) and the externalising problem vignette (PPV = 0.62). Conclusions The CCDT is a promising low-cost solution to overcome under-detection of children and families in need of mental healthcare. Future research should focus on evaluating the effectiveness, as well as additional strategies to improve help-seeking.

关键词： proactive detection Gatekeeper approach Help-seeking Children Adolescents Mental health Low-and middle-income countries Sri Lanka

来源：评论

学校读者我要写书评

暂无评论

Towards Adversarial Resilience in proactive detection of Botnet Domain Names by using MTD

Towards Adversarial Resilience in Proactive Detection of Bot...

引用

IEEE/IFIP Network Operations and Management Symposium (NOMS)

作者： Dietz, Christian Dreo, Gabi Sperotto, Anna Pras, Aiko Bundeswehr Univ Munich Res Inst CODE Neubiberg Germany Univ Twente Design & Anal Commun Syst Enschede Netherlands

ISBN: (纸本)9781728149738

Artificial Intelligence is often part of state-of-the-art Intrusion detection Systems. However, attackers use Artificial Intelligence to improve their attacks and circumvent IDS systems. Botnets use artificial intelligence to improve their Domain Name Generation Algorithms. Botnets pose a serious threat to networks that are connected to the Internet and are an enabler for many cyber-criminal activities (e.g., DDoS attacks, banking fraud and cyber-espionage) and cause substantial economic damage. To circumvent detection and prevent takedown actions, bot-masters use DGAs to create, maintain and hide C&C infrastructures. Furthermore, botmasters often release its source code to prevent detection, leading to numerous similar botnets that are created and maintained by different botmasters. As these botnets are based on nearly the same source code basis, they often share similar observable behavior. Current work on detection of DGAs is often based on applying machine learning techniques, as they are capable to generalize and to also detect yet unknown derivatives of a known botnets. However, these machine learning based classifiers can be circumvented by applying adversarial learning techniques. As a consequence, there is a need for resilience against adversarial learning in current Intrusion detection Systems. In our work, we focus on adversarial learning in DNS based IDSs from the perspective of a network operator. Further, we present our concept to make existing and future machine learning based IDSs more resilient against adversarial learning attacks by applying multi-level Moving Target Defense strategies.

关键词： Adversarial Learning Resilience DGA Botnet proactive detection

来源：评论

学校读者我要写书评

暂无评论

proactive Threat detection for Connected Cars Using Recursive Bayesian Estimation

引用

IEEE SENSORS JOURNAL 2018年第12期18卷 4822-4831页

作者： al-Khateeb, Haider Epiphaniou, Gregory Reviczky, Adam Karadimas, Petros Heidari, Hadi Univ Wolverhampton Wolverhampton Cyber Res Inst Sch Math & Comp Sci Wolverhampton WV1 1LY W Midlands England Northumbria Univ Dept Engn & Environm London Campus London E1 7HT England Univ Glasgow Sch Engn Glasgow G12 8QQ Lanark Scotland

Upcoming disruptive technologies around autonomous driving of connected cars have not yet been matched with appropriate security by design principles and lack approaches to incorporate proactive preventative measures in the wake of increased cyber-threats against such systems. In this paper, we introduce proactive anomaly detection to a use-case of hijacked connected cars to improve cyber-resilience. First, we manifest the opportunity of behavioral profiling for connected cars from recent literature covering related underpinning technologies. Then, we design and utilize a new data set file for connected cars influenced by the automatic dependent surveillance-broadcast surveillance technology used in the aerospace industry to facilitate data collection and sharing. Finally, we simulate the analysis of travel routes in real time to predict anomalies using predictive modeling. Simulations show the applicability of a Bayesian estimation technique, namely, Kalman filter. With the analysis of future state predictions based on the previous behavior, cyber-threats can be addressed with a vastly increased time window for a reaction when encountering anomalies. We discuss that detecting real-time deviations for malicious intent with the predictive profiling and behavioral algorithms can be superior in effectiveness than the retrospective comparison of known-good/known-bad behavior. When quicker action can be taken while connected cars encounter cyber-attacks, more effective engagement or interception of command and control will be achieved.

关键词： Connected cars cyber physical systems cyber threat proactive detection Bayesian estimation Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Big Data Analytics for proactive Financial Fraud detection and Prevention 2

Big Data Analytics for Proactive Financial Fraud Detection a...

引用

2nd International Conference on Technology Innovation and Its Applications, ICTIIA 2024

作者： Hasudungan, Yehezkeil Oganda, Fitra Putri Daeli, Ora Plane Maria Raihan Santoso, Nesti Anggraini University of Raharja Dept. of Informatics Engineering Tangerang Indonesia University of Raharja Dept. of Information System Tangerang Indonesia University of Raharja Dept. of Digital Business Tangerang Indonesia University of Raharja Dept. of Computer System Tangerang Indonesia

ISBN: (纸本)9798350351613

Financial fraud poses a significant challenge to the financial industry, with increasing complexity and scale threatening global economic stability. This paper explores the use of Big Data Analytics for proactive detection and prevention of financial fraud. By analyzing large and diverse datasets, this approach aims to identify patterns and anomalies that may indicate fraudulent activities before they harm financial institutions. In this study, Smart PLS is employed as the primary method to test the structural model and the influence of various variables on the effectiveness of fraud prevention. The findings reveal that integrating Big Data Analytics into fraud prevention strategies can enhance early detection and response to fraud threats, positively impacting financial risk management. This research contributes significantly to the field of risk management by offering a framework that can be implemented to enhance financial security through advanced data analytics. © 2024 IEEE.

关键词： Data Analytics Financial Fraud Prevention proactive detection Risk Management SmartPLS

来源：评论

学校读者我要写书评

暂无评论

Explainability Approach-Based Series Arc Fault detection Method for Photovoltaic Systems

引用

IEEE ACCESS 2024年 12卷 45530-45542页

作者： Wang, Yao Zhou, Jiawang Paul, Kamal Chandra Zhao, Tiefu Sheng, Dejie Hebei Univ Technol Sch Elect Engn Tianjin 300400 Peoples R China Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equipm Tianjin 300132 Peoples R China Univ North Carolina Charlotte Dept Elect & Comp Engn Charlotte NC 28223 USA

Arc fault detection devices are mandatory worldwide for mitigating DC series arc faults in photovoltaic systems. However, they are prone to nuisance tripping. Artificial intelligence-based approaches can be a solution, but they are "black boxes" and challenging to modify. This paper proposes an explainability and attention-based method to investigate the intensive details of such an algorithm. The contributions of an arc feature to the proposed model can be visualized by the proposed interpretable methodology so that insensitive arc features can be removed to reduce the quantity of input data. Additionally, the structure of the proposed model can be optimized by cutting the redundant layers. Thus, an accuracy of 99.63% is achieved with only 48.48% of the parameters compared to the original model. Finally, the optimized model is implemented by a Cortex M7-based microprocessor with a runtime of only 7.8 ms, making it ready for industrial application.

关键词： Feature extraction Fault detection Photovoltaic systems Fault diagnosis Computational modeling Discrete Fourier transforms Arc discharges Arc discharge artificial intelligence deep learning discrete Fourier transforms electrical fault detection electrical safety fault diagnosis machine learning photovoltaic systems proactive detection

来源：评论

学校读者我要写书评

暂无评论

Physics-Aware Watermarking Embedded in Unknown Input Observers for False Data Injection Attack detection in Cyber-Physical Microgrids

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 7824-7840页

作者： Liu, Mengxiang Zhang, Xin Zhu, Hengye Zhang, Zhenyong Deng, Ruilong Univ Sheffield Dept Automat Control & Syst Engn Sheffield S10 2TN England Zhejiang Univ State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China Zhejiang Univ Coll Control Sci & Engn Hangzhou 310027 Peoples R China

The physics-aware watermarking-based detection method has shown great potential in detecting stealthy False Data Injection Attacks (FDIAs) by adding appropriate watermarks to control commands or sensor measurements, especially in industrial control systems and grid-tied Distributed Energy Resources (DERs). However, existing watermarking-based detection methods have limitations in either handling the intricate physical couplings among DERs or characterising the fast changing power electronics dynamics, and thus cannot be directly applied to microgrids. Inspired by the methodology of Unknown Input Observer (UIO), which can be employed for the distributed anomaly monitoring in cyber-physical microgrids but would be easily bypassed once the adversary has the knowledge of certain electrical parameters, this paper makes the first attempt to investigate the physics-aware watermarking embedded in UIOs such that the stealthy FDIAs would be intentionally disrupted by the watermarking scheme. Based on the theoretical analysis of the detection enhancement and performance degradation under watermarking-enhanced UIOs, the watermark strengths, UIO parameters, and control gains are optimally co-designed to significantly enhance the detection effectiveness while not degrading the control performance. The robustness of the watermarking-enhanced UIO to Time Synchronisation Errors (TSEs) is improved by employing a sliding time window with appropriate length. The performance of the proposed method is validated through Matlab/Simulink studies and cyber-physical co-simulation experiments, and the sensitivities of the detection latency and TSE robustness to watermark strength and detection window's length are comprehensively studied.

关键词： False data injection attack microgrid physics-aware watermarking proactive detection unknown input observer cyber-physical co-simulation False data injection attack microgrid physics-aware watermarking proactive detection unknown input observer cyber-physical co-simulation

来源：评论

学校读者我要写书评

暂无评论

TL-LED^arcNet: Transfer Learning Method for Low-Energy Series DC Arc-Fault detection in Photovoltaic Systems

引用

IEEE ACCESS 2022年 10卷 100725-100735页

作者： Sung, Yoondong Yoon, Gihwan Bae, Ji-Hoon Chae, Suyong Korea Inst Energy Res KIER Dept Energy ICT Convergence Res Daejeon 34129 South Korea Daegu Catholic Univ DCU Dept AI & Big Data Engn Gyongsan 38430 South Korea Pohang Univ Sci & Technol POSTECH Dept Elect Engn Pohang 37673 South Korea

The arc-fault phenomenon in photovoltaic (PV) systems has emerged as a major problem in recent years. Existing studies on arc-fault detection in conventional PV systems primarily focus on detecting typical stable arc-faults. Low-energy arc-faults are more challenging to detect than stable arc-faults because of their low current distortions, short durations, and nonlinear properties. These low-energy arc-faults, which are precursors to stable arc-faults, could even inflict serious damage on the system components. Here, a transfer learning-based low-energy arc-fault detection network (TL-LEDarcNet) using a two-stage training method is proposed to proactively detect series DC arc-faults by considering low-energy arc-faults. A one-layer long short-term memory network combined with a lightweight one-dimensional convolutional neural network was developed to detect low-energy arc-faults by only using the sensed current information. The results of offline and online experiments conducted with a commercial grid-connected PV inverter indicate that the proposed method can perform real-time operations on a single-board computer and detect low-energy arc-faults with an accuracy of 95.8%, which is higher than previous methods considered in this study.

关键词： Inverters Circuit faults Photovoltaic systems Generators Fault detection Analytical models Transfer learning Long short term memory Long short-term memory low-energy arc-fault photovoltaic systems proactive detection transfer learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：