检索结果-内蒙古大学图书馆

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Ximing Li Linghui Li Xiaoyong Li Binsi Cai Bingyu Li Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China School of Cyber Science and Technology Beihang University Beijing China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Insider threats present a formidable challenge to cybersecurity, as insiders possess the privileges and information necessary to execute diverse attacks. A comprehensive analysis of user behavior, including behavioral features, sequences, and inter-user relationships, is required for effective insider threat detection. However, few existing methods consider these features in an integrated manner, which could result in high false positives. To further improve the accuracy of insider threat detection, we propose a novel framework for insider threat detection based on a temporal graph convolutional network with data augmentation (referred to as TGCN-DA), which integrates the exploration of structural information among users and simultaneously captures the behavior temporal dependencies. In particular, we introduce an edge predictor to encode user structural information and strengthen intra-class edges among users based on the representation of users’ behavior. Additionally, the GCN with temporal feature mechanism is leveraged to learn dynamic changes in users’ behavior to capture behavior temporal dependence. Extensive experiments demonstrate that our proposed TGCN-DA outperforms other state-of-the-art methods and achieves higher accuracy in the task of insider threat detection.

关键词： Data privacy Image edge detection Neural networks Data augmentation Feature extraction Threat assessment Task analysis

来源：评论

学校读者我要写书评

暂无评论

Feature-Adaptive and Data-Scalable In-Context Learning

arXiv

引用

arXiv 2024年

作者： Li, Jiahao Wang, Quan Zhang, Licheng Jin, Guoqing Mao, Zhendong University of Science and Technology of China Hefei China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China People’s Daily Online Co. Beijing China

In-context learning (ICL), which promotes inference with several demonstrations, has become a widespread paradigm to stimulate LLM capabilities for downstream tasks. Due to context length constraints, it cannot be further improved in spite of more training data, and general features directly from LLMs in ICL are not adaptive to the specific downstream task. In this paper, we propose a feature-adaptive and data-scalable in-context learning framework (FADS-ICL), which can leverage task-adaptive features to promote inference on the downstream task, with the supervision of beyond-context samples. Specifically, it first extracts general features of beyond-context samples via the LLM with ICL input form one by one, and introduces a task-specific modulator to perform feature refinement and prediction after fitting a specific downstream task. We conduct extensive experiments on FADS-ICL under varying data settings (4∼128 shots) and LLM scale (0.8∼70B) settings. Experimental results show that FADS-ICL consistently outperforms previous state-of-the-art methods by a significant margin under all settings, verifying the effectiveness and superiority of FADS-ICL. For example, under the 1.5B and 32 shots setting, FADS-ICL can achieve +14.3 average accuracy from feature adaptation over vanilla ICL on 10 datasets, with +6.2 average accuracy over the previous state-of-the-art method, and the performance can further improve with increasing training data. Code and data are publicly available at https://***/jiahaozhenbang/FADS-ICL. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning based time-domain mutual interference avoidance for automotive radar

Reinforcement learning based time-domain mutual interference...

引用

IET International Radar Conference (IRC 2023)

作者： He Xiao Jianping Wang Runlong Li Yuan He Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing People's Republic of China Faculty of EEMCS Delft University of Technology Delft Netherlands

ISBN: (数字)9781837240982

Due to the extensive usage of automotive radars on vehicles, mutual interference among radars on the road is becoming considerable. To address this, we propose a time domain strategy based on deep reinforcement learning (DRL). This approach helps avoid mutual interference for automotive radars in the time domain without extra communications. The numerical simulation results demonstrate that the proposed approach can avoid interference as effectively as frequency hopping. Moreover, the time domain strategy has more advantages than frequency hopping when encountering dynamic interference.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DACTI: a Generation-Based Data Augmentation Method for Cyber Threat Intelligence

DACTI: a Generation-Based Data Augmentation Method for Cyber...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Jingbing Chen Yali Gao Xiaoyong Li Key Lab of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

Methods of data augmentation are extensively utilized to boost the efficacy of machine learning, given their superior capability in promoting generalization performance. In this paper, we address the issue of data scarcity in the field of cyber threat intelligence and propose a method for generating high-quality synthetic data by training a language model on linearized labeled phrases. Subsequently, we design a relational classification model to classify relational entities related to cyber threat intelligence in the created synthetic data. We conduct extensive experiments on datasets of different sizes, and the experimental results show that our proposed method outperforms the baseline methods, especially when the amount of gold data provided is insufficient, and the $F_{1}$ score of our model is improved by up to 1.94 points.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fundamentalists, Integrationists, & Transformationists: An Empirical Theory of Men Software Engineers’ Orientations in Gender Inequalities

Fundamentalists, Integrationists, & Transformationists: An E...

引用

IEEE/ACM International Conference on Software Engineering: Software Engineering in Society Track (ICSE-SEIS)

作者： Yi Wang Xinyue Zhang Wei Wang Beijing University of Posts and Telecommunications Beijing P.R. China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) MoE Beijing P.R. China

Professional software development is an occupation dominated by men software engineers. Recently, researchers have been investigating gender inequality in the software development profession from multiple perspectives. While most of the extant literature on gender inequality in software development takes the perspective of female developers, the vast majority of the software development workforce–men software engineers–receives much less attention. In this article, we reported on a quantitative interview study aiming at developing empirical understandings of men software engineers’ orientations in gender inequalities. Through analyzing interview narratives from 21 professional men software engineers, plenty of findings emerged, enabling us to build a theoretical framework characterizing three different types of orientations in gender inequalities. In our theory, men software engineers’ orientation in gender issues could be conceptualized as fundamentalists, integrationists, and transformationists. We introduced each type’s characteristics from three aspects of individuals’ social cognition, which are belief, attitude, and action. We further discussed the implications and the limitations of the study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tree-IDS: An Incremental Intrusion Detection System for Connected Vehicles

Tree-IDS: An Incremental Intrusion Detection System for Conn...

引用

Conference on Local Computer Networks (LCN)

作者： Yuxin Zhao Zixiang Bi Guosheng Xu Chenyu Wang Guoai Xu Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen China

The rapid development of Internet of Vehicles technology has led to the continuous upgrading of the functions of connected vehicles. While connected vehicles bring convenience to people’s life, there are also many security threats. Connected vehicles not only have intra-vehicle networks communication, but also communicate with the external network. The diversity of communication methods makes the attack surface wider, and some new attacks are constantly emerging. In order to ensure vehicle security, This paper focuses on the attacks that are vulnerable to vehicles, and proposes an incremental intrusion detection system, which can not only detect attacks, but also incrementally learn new types of attacks. Experimental results illustrate that the proposed system can incrementally learn new attacks and avoid catastrophic forgetting problems, and can detect various types of known attacks with 99.99% accuracy on the Car-Hacking Dataset and 99.37% accuracy on the CICIDS2017.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Local Interpretability Model-Based Approach for Black-Box Adversarial Attack 8th

A Local Interpretability Model-Based Approach for Black-Box ...

引用

8th International Conference on Data Mining and Big Data, DMBD 2023

作者： Duan, Yuanjie Zuo, Xingquan Huang, Hai Wu, Binglin Zhao, Xinchao School of Computer Science Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China School of Science Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9789819708437

Deep learning models are vulnerable to adversarial examples due to their fragility. Current black-box attack methods typically add perturbations to the whole example, and added perturbations may be large and easily detected by human eyes. This study proposes a Local Interpretable Model-agnostic Explanations (LIME)-based approach for black-box adversarial Attack (LIME-Attack). The approach can reduce the size of perturbations via adding perturbations in discriminative regions of an example. First, LIME is used to interpret a black-box model to obtain discriminative regions of an example. Then, the gradient information of the example is estimated by a derivative-free optimization method (Nature Evolution Strategy). Utilizing the gradient information, two white-box attack methods are adapted to generate perturbations, which are added in discriminative regions of the example to form an adversarial example. LIME-Attack is applied to several typical neural network models. Experiments show that it can achieve a high attack success rate with perturbation size 10%–30% lower than that of comparative methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

ModalSync: Synchronizing User Behavior with Multimodal Features for Multimodal Pre-training Recommendation 25

ModalSync: Synchronizing User Behavior with Multimodal Featu...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Shiqin Liu Chaozhuo Li Minjun Zhao Litian Zhang Jiajun Bu College of Computer Science and Technology Zhejiang University Hangzhou China Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications Beijing China School of Cyber Science and Technology Beihang University Beijing China

ISBN: (纸本)9798400713316

In the continually evolving landscape of online platforms, integrating multimodal information into recommender systems offers a promising avenue to enhance our understanding of user preferences and product insights. Traditional models primarily rely on user-item interactions, but the advent of multimodal systems utilizes additional data modalities-text, images, audio, and video-to enhance recommendation accuracy. However, existing multimodal recommendation architectures often fail to fully exploit the potential synergy between multimodal feature extraction and recommendation processes, leading to domain bias and false positives. In this work, we introduce ModalSync, a novel multimodal pre-training framework designed to synchronize multimodal features with user behaviors, closely aligning with human perceptual processes. Unlike previous approaches that utilize pre-trained generic encoders, ModalSync incorporates a pre-training method that integrates both unsupervised and supervised strategies, thereby fostering a harmonious relationship between interaction graphs and multimodal data. Our framework uniquely addresses domain bias by infusing recommendation-specific interaction data into the feature extraction process and reduces false positives by directing encoder attention towards crucial attributes. Furthermore, ModalSync introduces a staged co-training module that strategically adjusts the training dynamics of the feature extractors and GNNs, promoting an effective and seamless fusion of multimodal information. Extensive experiments across three public datasets demonstrate that ModalSync significantly outperforms existing methods, achieving state-of-the-art results.

关键词： graph neural network

来源：评论

学校读者我要写书评

暂无评论

WBRP: Consensus Algorithm Based on Weak Proof of Work

WBRP: Consensus Algorithm Based on Weak Proof of Work

引用

IEEE International Conference on Blockchain (Blockchain)

作者： Jiarui Li Dongbin Wang Hui Zhi Wencheng Zhu Jianing Li Zedong Wang School of Cyberspace Engineering Beijing University of Post and Telecommunications Beijing China National Engineering Laboratory for Mobile Network Beijing China TravelSky Technology Limited Beijing China Key Laboratory of Ministry of Education and Trustworthy Distributed Computing and Service Beijing China

ISBN: (数字)9798350351590

ISBN: (纸本)9798350351606

Nakamoto Consensus (NC) is a classic Proof of Work (PoW) consensus algorithm where the probability of miners earning the right to a block is proportional to their computational power. To prevent blockchain forks, the interval between block outputs is restricted, which results in lower throughput for PoW. To address blockchain performance issues, a transaction ledger scheme based on weak PoW consensus has been proposed. This approach combines strong and weak blocks, allowing miners to submit weak blocks with lower mining difficulty. Nodes can then use these weak blocks to organize transaction information on the main chain and ensure strict linear ordering of blocks and transactions through sorting rules. Experimental results demon-strate that the consensus algorithm based on weak PoW can significantly enhance system performance, allowing transaction throughput to increase linearly with bandwidth. Specifically, with a node bandwidth of 1 Gb/s, the performance can exceed NC by more than 300 times.

关键词： System performance Consensus algorithm Bandwidth Throughput Proof of Work Extensibility Blockchains

来源：评论

学校读者我要写书评

暂无评论

Research on the Electric Energy Metering Data Sharing Method in Smart Grid Based on Blockchain

引用

Journal on Big Data 2023年第1期5卷 57-67页

作者： Shaocheng Wu Honghao Liang Xiaowei Chen Tao Liu Junpeng Ru Qianhong Gong Jin Li Shenzhen Power Supply Co. Ltd.Shenzhen518001China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Beijing100876China

Enabling data sharing among smart grid power suppliers is a pressing challenge due to technical hurdles in verifying,storing,and synchronizing energy metering *** and sharing limitations are stringent for users,power companies,and researchers,demanding significant resources and time for permissions and *** paper proposes a blockchain-based architecture for secure and efficient sharing of electric energy metering ***,we propose a data sharing model based on evolutionary game *** on the Lyapunov stability theory,the model’s evolutionary stable strategy(ESS)is *** results verify the correctness and practicability of the scheme proposed in this paper,and provide a new method for realizing convenient,safe and fast data sharing.

关键词： Smart grid data sharing blockchain evolutionary stable strategy

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：