检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yitong Cai Chengwei Peng Shu Li Yuyi Liu Hongfei Zhang Binxing Fang Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Deep learning-based malicious traffic detection requires large-scale, accurately labeled datasets. However, realistic malicious traffic datasets contain noisy labels due to annotation errors, which can degrade the performance of detection models. Existing methods for handling noisy labels involve robust training or data cleaning. However, both approaches risk excluding hard samples from model update, leading to suboptimal decision boundaries and reduced classification performance. To this end, we introduce TRACE, a novel framework that leverages multi-loss optimization to induce robust traffic representations while utilizing all samples. TRACE utilizes a one-dimensional convolutional neural network (1D CNN) with multi-head attention to generate fine-grained traffic representations. Then, TRACE employs multi-loss optimization to enhance representation robustness, ensuring representation integrity and class separability, thereby laying the foundation for effective decision boundaries. The experimental results on two public datasets demonstrate that TRACE achieves an accuracy of 88.3% and an F1-score of 81% with 90% label noise, outperforming the state-of-the-art methods.

关键词： Training Accuracy Annotations Noise Robustness Cleaning Noise measurement Convolutional neural networks Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

VulnerGAN: a backdoor attack through vulnerability amplification against machine learning-based network intrusion detection systems

引用

Science China(Information Sciences) 2022年第7期65卷 32-50页

作者： Guangrui LIU Weizhe ZHANG Xinjie LI Kaisheng FAN Shui YU School of Cyberspace Science Harbin Institute of Technology Cyberspace Security Research Center Peng Cheng Laboratory School of Computer Science University of Technology Sydney

Machine learning-based network intrusion detection systems(ML-NIDS) are extensively used for network security against unknown attacks. Existing intrusion detection systems can effectively defend traditional network attacks, however, they face AI based threats. The current known AI attacks cannot balance the escape rate and attack effectiveness. In addition, the time cost of existing AI attacks is very high. In this paper, we propose a backdoor attack called VulnerGAN, which features high concealment,high aggressiveness, and high timeliness. The backdoor can make the specific attack traffic bypass the detection of ML-NIDS without affecting the performance of ML-NIDS in identifying other attack *** uses generative adversarial networks(GAN) to calculate poisoning and adversarial samples based on machine learning model vulnerabilities. It can make traditional network attack traffic escape black-box online ML-NIDS. At the same time, model extraction and fuzzing test are used to enhance the convergence of VulnerGAN. Compared with the state-of-the-art algorithms, the VulnerGAN backdoor attack increases33.28% in concealment, 18.48% in aggressiveness, and 46.32% in timeliness.

关键词： AI security adversarial sample data poisoning network intrusion detection generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

A Cross-chain Model Based on Credit Hierarchical Notary Group for IoT Roaming Settlement 6th

A Cross-chain Model Based on Credit Hierarchical Notary Gro...

引用

6th International Conference on Blockchain and Trustworthy Systems, BlockSys 2024

作者： Lu, Shuhao Liang, Hai Wang, Yujue Ding, Yong Yang, Changsong Guo, Zhenwei Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Engineering Research Center of Industrial Internet Security and Blockchain Guilin University of Electronic Technology Guilin China Hangzhou Innovation Institute of Beihang University Hangzhou China Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Nanning China Institute of Cyberspace Technology HKCT Institute for Higher Education Hong Kong

ISBN: (纸本)9789819614134

In IoT with Blockchain, an increasing number of mobile IoT devices are starting to work across various locations, requiring operators connected to these IoT devices to provide roaming services. Due to the differences in the blockchains used by operators, a safe and efficient cross-chain model for IoT device roaming settlement is significant for operators. In this paper, a cross-chain model based on credit hierarchical multi-notary is proposed to connect different blockchains in IoT devices roaming settlement. Firstly, a cross-chain election method by sub-notary group is proposed to solve the problem of "Richer Get Richer" in blockchain with credit scheme and avoid risk of malicious notary nodes. Secondly, a re-election mechanism is used to make the process of cross-chain running properly with the number of IoT devices is increasing rapidly and transaction concurrency. Moreover, a weighted voting system is designed for sub-notary group cross-chain model to reduce the influence of malicious notary nodes. Experimental results demonstrate that the proposed cross-chain model performs better on credit ecology and defending malicious nodes’ influence than the model without sub-notary mechanism. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

SDN load balancing method based on K-dijkstra

引用

International Journal of Performability Engineering 2018年第4期14卷 709-716页

作者： Yang, Xiaohui Wang, Lei School of Cyberspace Security and Computer Hebei University Baodin071002 China

In order to solve the problem that control and forwarding are closely coupled in traditional network, the network lack of innovation and programmability, and the network management and maintenance difficulty, an SDN load balancing method based on K-Dijkstra is proposed. By using SDN technology to achieve the separation of control and forwarding, the controller is responsible for the global scheduling, making the network flow and task scheduling more flexible than the traditional network. Through the integration of flow management, traffic monitoring, dynamic load balancing and load calculation in the SDN control layer, the K-Dijkstra algorithm and the HRRF algorithm are combined in the load balancing module to solve the problem of path selection. The traffic environment also has a better load balancing effect, optimizing the control layer structure, improving network management efficiency and achieving dynamic load balancing of network traffic. The simulation results on Mininet show that the method can significantly improve network delay, packet loss and throughput compared with traditional networks. © 2018 Totem Publisher, Inc. All rights reserved.

关键词： Network management

来源：评论

学校读者我要写书评

暂无评论

SecPQ: Secure Prediction Queries on Encrypted Outsourced Databases

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Liang, Jinwen Guo, Song Hong, Zicong Zhou, Enyuan Zhang, Chuan Xiao, Bin Hong Kong Polytechnic University Hung Hom Department of Computing Kowloon Hong Kong Hong Kong University of Science and Technology Clear Water Bay Department of Computer Science and Engineering Kowloon Hong Kong Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong China

Prediction queries have revolutionized data search by integrating machine learning models and traditional data processing operations for advanced analytics. However, existing prediction query frameworks for outsourced databases face a critical security vulnerability: data flows are processed in plaintext on semi-honest servers, making them susceptible to data breaches. The main challenge in achieving secure prediction queries is that machine learning inference and data processing operations are distinct functionalities, while most current cryptographic frameworks support only a single type of operation on specific encrypted data. To bridge this crucial gap, we propose SecPQ, the first framework tailored for secure prediction queries. Our approach unifies decision tree pipelines and data processing operations, such as selection, projection, and equality-joining, through equality matching on encrypted outsourced data. This enables the design of secure prediction queries with decision tree pipelines operating on encrypted data. We provide formal security definitions and proofs for SecPQ. To further optimize the efficiency of secure prediction queries, we leverage order-preserving encryption to construct SecPQope, which offers improved query efficiency at the expense of weaker security properties compared with SecPQ. Extensive experimental evaluations on billions of records demonstrate the feasibility and effectiveness of both SecPQ and SecPQope. © 2004-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Comparing Different Membership Inference Attacks with a Comprehensive Benchmark

引用

IEEE Transactions on Information Forensics and security 2025年

作者： Niu, Jun Zhu, Xiaoyan Zeng, Moxuan Zhang, Ge Zhao, Qingyang Huang, Chunhui Zhang, Yangming An, Suyu Wang, Yangzhong Yue, Xinghui He, Zhipeng Guo, Weihao Shen, Kuo Liu, Peng Zhang, Lan Ma, Jianfeng Zhang, Yuqing Xidian University School of Cyber Engineering School of Computer Science and Technology Xi'an710071 China Xidian University School of Telecommunications Engineering Xi'an710071 China Xidian University School of Hangzhou Institute of Technology Hangzhou311231 China Pennsylvania State University Information Sciences and Technology 16802 United States Northern Arizona University The School of Informatics Computing & Cyber Systems FlagstaffAZ86005 United States Xidian University School of Cyber Engineering Xi'an710071 China Yanshan University The College of Information Science and Engineering Qinhuangdao066004 China University of Chinese Academy of Sciences The School of Computer Science and Technology Beijing101408 China The School of Cyberspace Security Hainan University Haikou570228 China

Membership inference (MI) attacks pose a significant threat to user privacy in machine learning. While numerous attacks have been proposed, the lack of standardized evaluation parameters and metrics has led to inconsistent and even conflicting comparison results. To address this issue and facilitate a systematic analysis of these disparate findings, we introduce MIBench, a comprehensive benchmark that includes a suite of carefully designed evaluation scenarios (ESs) and evaluation metrics to provide a consistent framework for assessing various MI techniques. The ESs are crafted to encompass four critical factors: intra-dataset distance distribution, inter-sample distance within the target dataset, differential distance analysis, and inference withholding ratio. MIBench includes ten typical evaluation metrics and 84 distinct ESs per dataset. Using MIBench, we conducted a thorough comparative analysis of 15 state-of-the-art MI attacks across 588 ESs, seven widely adopted datasets, and seven representative model architectures. Our analysis revealed 83 instances of Conflicting Comparison Results (CCR), providing substantial evidence for the CCR Phenomenon. We identified two CCR types: Type 1 (single-factor) and Type 2 (dual-factor). The CCR distribution across four factors was: inter-sample distance (40.96%), differential distance (37.35%), inference withholding ratio (19.28%), and intra-dataset distance (2.41%). All MIBench codes and evaluations are available at link. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Conformal Graph-level Out-of-distribution Detection with Adaptive Data Augmentation 25

Conformal Graph-level Out-of-distribution Detection with Ada...

引用

Proceedings of the ACM on Web Conference 2025

作者： Xixun Lin Yanan Cao Nan Sun Lixin Zou Chuan Zhou Peng Zhang Shuai Zhang Ge Zhang Jia Wu Institute of Information Engineering Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Cyber Science and Engineering Wuhan University Wuhan China School of Cyber Security University of Chinese Academy of Sciences Academy of Mathematics and Systems Science CAS Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China Academy of Mathematics and Systems Science CAS Beijing China School of Computer Science and Technology Donghua University Shanghai China Department of Computing Macquarie University Sydney Australia

ISBN: (纸本)9798400712746

Graph-level out-of-distribution (OOD) detection, which attempts to identify OOD graphs originated from an unknown distribution, is a vital building block for safety-critical applications in Web and society. Current approaches concentrate on how to learn better graph representations, but fail to provide any statistically guarantee on detection results, therefore impeding their deployments in the scenario where detection errors would result in serious consequences. To overcome this critical issue, we propose the Conformal Graph-level Out-of-distribution Detection (CGOD), extending the theory of conformal prediction to graph-level OOD detection with a rigorous control over the false positive rate. In CGOD, we develop a new aggregated non-conformity score function based on the proposed adaptive data augmentation. Through the guidance from two designed metrics, i.e., score consistency and representation diversity, our augmentation strategy can generate multiple non-conformity scores, and aggregating these generated non-conformity scores together is robust to the misleading information. Meanwhile, our score function can perceive the subsequent process of conformal inference, enabling the aggregated non-conformity score to be adaptive to different input graphs and deriving a more accurate score estimation. We conduct experiments on multiple real-world datasets with different empirical settings. Extensive results and model analyses demonstrate the superior performance of our approach over several competitive baselines.

关键词： conformal prediction

来源：评论

学校读者我要写书评

暂无评论

pFedCal: Lightweight Personalized Federated Learning with Adaptive Calibration Strategy

引用

IEEE Transactions on Services Computing 2025年

作者： Deng, Dongshang Wu, Xuangou Zhang, Tao Xiang, Chaocan Zhao, Wei Xu, Minrui Kang, Jiawen Han, Zhu Niyato, Dusit Anhui University of Technology School of Computer Science and Technology Anhui Province Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Ma'anshan243002 China Beijing Jiaotong University School of Cyberspace Science and Technology Beijing100044 China Anhui Provincial Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui243002 China Chongqing University College of Computer Science Chongqing400044 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Guangdong University of Technology School of Automation Guangzhou510062 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Federated learning (FL) is a promising artificial intelligence framework that enables clients to collectively train models with data privacy. However, in real-world scenarios, to construct practical FL frameworks, several challenges have to be addressed, including statistical heterogeneity, constrained resources, and fairness. Therefore, we first investigate an aggregation gap caused by statistical heterogeneity during local model initialization, which not only causes additional computational overhead for clients but also leads to the degradation of fairness. To bridge this gap, we propose pFedCal, a novel personalized federated learning with lightweight adaptive calibration strategy that performs calibration compensation through the prior knowledge of clients. Specifically, we introduce compensation for each client at the model initialization, with the compensation derived from the global gradient and the latest gradient bias. To enhance the calibration effect, we introduce a smoothing-based calibration strategy, and we design an adaptive calibration strategy. A representative example demonstrates that the proposed calibration and smoothing strategies improve fairness for clients. The theoretical analysis indicates that with an appropriate learning rate, pFedCal converges to a first-order stationary point for non-convex loss functions. Comprehensive experimental results show that pFedCal achieves faster convergence, higher accuracy, and improved fairness than the state-of-the-art methods. © 2008-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

New MRA Schemes Based on The CRT for Polynomial Rings

引用

IEEE Transactions on Information Theory 2025年

作者： Yang, Jing Wang, Xianfang Xiang, Can Fu, Fang-Wei Xia, Shu-Tao Shandong Technology and Business University School of Computer Science and Technology Shandong Yantai264005 China CETC Cyberspace Security Technology Co. Ltd Westone Cryptologic Research Center Beijing100070 China South China Agricultural University College of Mathematics and Informatics Guangdong Guangzhou510642 China Nankai University Chern Institute of Mathematics LPMC Tianjin300071 China Tsinghua University Tsinghua Shenzhen International Graduate School Guangdong Shenzhen518055 China

At present, existing multi-receiver authentication (MRA) schemes can only handle situations where the capacities of all receivers in the schemes are the same. However, in reality, different receivers may need to have different storage capacities. In this paper, inspired by the secret sharing scheme based on the Chinese Remainder Theorem (CRT) for polynomial rings where each participant holds the share with different sizes, we propose three new constructions of unconditionally secure MRA schemes for multiple messages using the CRT for polynomial rings, including a (k, n)-threshold MRA scheme, a (k, n, w)-weighted threshold MRA scheme, and a (Q, F)-general MRA scheme. As far as we know, our proposed MRA schemes are the first MRA schemes with different storage capacities for different receivers and the first ones based on the CRT for polynomial rings. Moreover, the proposed schemes can be seen as extensions of the MRA scheme in Safavi-Naini and Wang (Eurocrypt’98, LNCS, 1403, 527-541, 1998). In particular, as for our (Q, F)-general MRA scheme, it has generally more communication complexity and much less computation complexity than the existing (Q, F)- general MRA scheme. © 1963-2012 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

PROBABILISTIC AND AVERAGE LINEAR WIDTHS OF SOBOLEV SPACE WITH GAUSSIAN MEASURE IN SPACE S_Q(T)(1≤Q≤∞)

引用

Acta Mathematica Scientia 2015年第2期35卷 495-507页

作者：徐艳艳陈广贵甘莹许燕 Lab of Security Insurance of Cyberspace of Sichuan Province School of Mathematics and Computer EngineeringXihua University School of Mathematics and Computer Engineering Xihua University

Probabilistic linear （N, δ）-widths and p-average linear N-widths of Sobolev space W2^r（T）, equipped with a Gaussian probability measure #, are studied in the metric of Sq （T）（1 ≤ Q ≤∞）, and determined the asymptotic equalities： λN,δ（W2^r（T）,μ,Sq（T））={（N^-1）^r＋p/2-1/q√1＋1/N·ln1/δ, 1≤q≤2, （N^-1）^r＋p/2-1/q（1＋N^-1/q√ln1/δ）,2〈q〈∞, （N^-1）^r＋p/2√lnN/δ, q=∞, and λN^（a）（W2^r（T）,μ,Sq（T））p={（N^-1）^r＋p/2-1/q, 1≤q〈∞, （N^-1）^r＋p/2-1/q√lnN, q=∞, where 0 〈 p 〈 ∞, δ∈ （0, 1/2], ρ 〉 1, and Sq（T） is a subspace of L1（T）, in which the Fourier series is absolutely convergent in lq sense.

关键词： Probabilistic linear width Average linear width Gaussian measure Sobolevspace linear operator

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：