检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Minghui Wan, Wei Ning, Yuxuan Hu, Shengshan Xue, Lulu Zhang, Leo Yu Wang, Yichen School of Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development. To bridge this gap, we present DarkFed. Initially, we emulate a series of fake clients, thereby achieving the attacker proportion typical of academic research scenarios. Given that these emulated fake clients lack genuine training data, we further propose a data-free approach to backdoor FL. Specifically, we delve into the feasibility of injecting a backdoor using a shadow dataset. Our exploration reveals that impressive attack performance can be achieved, even when there is a substantial gap between the shadow dataset and the main task dataset. This holds true even when employing synthetic data devoid of any semantic information as the shadow dataset. Subsequently, we strategically construct a series of covert backdoor updates in an optimized manner, mimicking the properties of benign updates, to evade detection by defenses. A substantial body of empirical evidence validates the tangible effectiveness of DarkFed. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Li, Bowen Song, Yufei Yu, Zhifei Hu, Shengshan Wan, Wei Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within images. We directly leverage the features output by the OD without relying on its internal structures to craft adversarial examples. Specifically, we first design a dual-track attack target selection strategy to select high-quality bounding boxes from OD outputs for targeting. Subsequently, we employ directional perturbations to shift and compress predicted boxes and change classification results to deceive ODs. Additionally, we focus on manipulating the high-frequency components of images to confuse ODs' attention on critical objects, thereby enhancing the attack efficiency. Our extensive experiments on nine ODs and two datasets show that NumbOD achieves powerful attack performance and high stealthiness. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PB-UAP: Hybride Universal Adversarial Attack for Image Segmentation

PB-UAP: Hybride Universal Adversarial Attack for Image Segme...

引用

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

作者： Yufei Song Ziqi Zhou Minghui Li Xianlong Wang Hangtao Zhang Menghao Deng Wei Wan Shengshan Hu Leo Yu Zhang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, i.e., adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the model’s predicted labels. Due to the output complexity and deeper network architectures, research on adversarial examples for segmentation models is still limited, particularly for universal adversarial perturbations. In this paper, we propose a novel universal adversarial attack method designed for segmentation models, which includes dual feature separation and low-frequency scattering modules. The two modules guide the training of adversarial examples in the pixel and frequency space, respectively. Experiments demonstrate that our method achieves high attack success rates surpassing the state-of-the-art methods, and exhibits strong transferability across different models.

关键词： Training Image segmentation Perturbation methods Semantics Scattering Signal processing Predictive models Network architecture Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

Optimized Dynamic Watermarking for Audio DNNs with Adaptive Embedding and Boundary Sampling

Optimized Dynamic Watermarking for Audio DNNs with Adaptive ...

引用

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

作者： Hao Fei Hewang Nie Siqi Sun Songfeng Lu Ting Luo Ling Qian Dunbo Cai Zhiguo Huang Runqing Zhang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China China Mobile (Suzhou) Software Technology Company Limited Suzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The intensified concerns arising from the widespread adoption of deep learning have led to increased scrutiny of intellectual property protection in DNN models. Existing audio watermarking techniques, predominantly based on traditional signal processing methods, struggle to balance robustness, imperceptibility, and defense resistance in the face of evolving adversarial attacks. These limitations underscore the urgent need for more effective watermarking solutions in the audio domain. In this paper, we propose a dynamic audio watermarking framework that introduces an optimization-based approach to attach robust and adaptable triggers at arbitrary positions within audio signals, and innovatively integrates boundary sample selection driven by forgetting events and an adaptive watermark trigger embedding technique based on the SNR. Comprehensive experimental results reveal that our scheme preserves high model performance while maintaining remarkable stealthiness and robustness, offering a secure and reliable solution for safeguarding intellectual property in the audio domain and advancing the field of DNN watermarking.

关键词： Resistance Deep learning Adaptation models Watermarking Intellectual property Signal processing Robustness Speech processing Protection Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Triangular Stable Node Network based on Self-supervised Learning for personalized prediction

A Triangular Stable Node Network based on Self-supervised Le...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Qing Gao, Qian Fan, Jun Zhang, Zhiqiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250014 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan250014 China China Telecom Digital Intelligence Techonology Co Ltd. No.1999 Shunhua road Shandong Jinan250101 China

ISBN: (纸本)9798350368741

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN-a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model's effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets. © 2025 IEEE.

关键词： graph contrastive learning graph neural networks recommender systems self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

MalWuKong: Towards Fast, Accurate, and Multilingual Detection of Malicious Code Poisoning in OSS Supply Chains

MalWuKong: Towards Fast, Accurate, and Multilingual Detectio...

引用

IEEE International Conference on Automated Software engineering (ASE)

作者： Ningke Li Shenao Wang Mingxi Feng Kailong Wang Meizhen Wang Haoyu Wang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

In the face of increased threats within software registries and management systems, we address the critical need for effective malicious code detection. In this paper, we propose an innovative approach that integrates source code slicing, inter-procedural analysis, and cross-file inter-procedural analysis, thereby enhancing the detection precision and reducing false positives. This approach has been encapsulated within a multi-analysis-based framework for automatic detection of malicious code in real-world software packages. In its application to major third-party software registries like PyPI and NPM, our framework has proven effective, identifying 130 malicious packages from a total of 169,640 monitored over a continuous period of five weeks. This work advances the current state-of-the-art solution to malicious code detection, demonstrating significant practical impact in strengthening the software supply chain defense.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Programming Course Quality through Human Posture Recognition and Screen Content Detection

Enhancing Programming Course Quality through Human Posture R...

引用

Information Science and Education (ICISE-IE), International Conference on

作者： Xiaopan Chen Haiyang Bai Xiaoke Zhu Lingyuan Dong School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

The evaluation of programming course instruction is a key component of educational management. However, relying solely on supervising teachers for assessment poses challenges in comprehensive evaluation and providing feedback on students' classroom learning status. Additionally, a significant amount of monitoring video data from programming courses in Chinese universities remains underutilized. To address these challenges, this paper combines traditional educational management with artificial intelligence and proposes an intelligent algorithm for detecting students' learning status in programming courses. We first establish a dual YOLO network model to analyze students' postures and screen content in programming classroom monitoring videos, thereby identifying their behaviors. Subsequently, we develop a Programming Classroom Student Behavior Recognition System (PCSBS) that integrates data collection, student behavior detection, and result visualization functionalities. Experimental results demonstrate that the system can accurately provide feedback on students' programming course learning status, offering graded results that assist supervising teachers in their classroom instructional evaluation tasks to enhance educational management efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Distractibility Induced trust Management Using BlockChain for Edge Computing

Towards Distractibility Induced trust Management Using Block...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2021

作者： Yang, Haochen Wang, Guanghui Dong, Lifeng He, Xin School of Software Henan University Kaifeng China Henan Provincial Engineering Research Center of Intelligent Data Processing Kaifeng China Henan International Joint Laboratory of Intelligent Network Theory and Key Technology Henan University Kaifeng China Institute of Intelligent Network System Henan University Kaifeng China Henan Jiuyu Tenglong Information Engineering Co. Ltd. Zhengzhou China

ISBN: (纸本)9789811669620

Edge computing solves massive data processing problems by utilizing the storage and computing functions of edge devices. Due to the openness of edge computing, distracted devices inevitably participate in edge computing and affect the network computing performance, which degrades trust management of edge devices. To solve the above issue, this paper proposes a trust management framework based on blockchain for edge computing scenarios (ECTMF). First, the ECTMF framework slices users and provides corresponding services based on different requirements. It evaluates the trustworthiness of end devices and distinguishes distracted devices in edge computing. Then, the Proof of Monitor (PoM) consensus mechanism is proposed to continuously monitor distracted end devices in edge computing. Simulations validate the effectiveness and efficiency of the ECTMF and PoM. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Automated Extraction of Active Offshore Oil/Gas Platforms Based on High-Spatial Resolution SDGSAT-1/GLI data: A Case Study in the Northern Gulf of Mexico 2

Automated Extraction of Active Offshore Oil/Gas Platforms Ba...

引用

2023 2nd International Conference on Environmental Remote Sensing and Geographic Information technology, ERSGIT 2023

作者： Chen, Zhongzhong Yan, Lin Qiu, Yujia Liang, Yueji Li, Xiao-Ming College of Geomatics and Geoinformation Guilin University of Technology Guilin541004 China International Research Center of Big Data for Sustainable Development Goals Beijing100094 China Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Computer and Information Engineering Henan University Kaifeng475001 China

ISBN: (纸本)9781510672949

The acquisition of spatial distribution information on active offshore oil/gas platforms (AOOP) is of importance for effective ocean management and the comprehensive study on marine carbon emissions. In recent years, the methodological framework for AOOP extraction using low-light remote sensing imagery has emerged as a novel and promising approach. Consequently, in this study, we utilized high-resolution low-light images obtained from the Glimmer Imager (GLI) payload aboard the Sustainable Development Goals Science Satellite 1 (SDGSAT-1) to facilitate the automatic extraction of AOOP. We applied a time-series low-light remote sensing (TLLRS) method for automatic extraction of AOOP in the northern Gulf of Mexico for the year 2022. The results indicate that the TLLRS method achieves a remarkable precision rate of 95.31% in the automatic extraction of AOOP, with an overall accuracy of 84.92%. Our findings demonstrate the feasibility and efficacy of applying SDGSAT-1 GLI data to monitor AOOP at large-scale. © 2024 SPIE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Clustering Network Based on Pre-Clustering center Codebook

Clustering Network Based on Pre-Clustering Center Codebook

引用

International Conference on Intelligent System and Knowledge engineering, ISKE

作者： Qiulong An Jianning Wu Tianqiang Huang Liqing Huang Haifeng Luo Feng Ye Fujian Provincial Engineering Research Center of Big Data Analysis and Application College of Computer and Cyber Security Fujian Normal University Digital Fujian Institute of Big Data Security Technology Fuzhou China

Most existing deep clustering models attempt to group similar datas by using autoencoders to simultaneously minimize the clustering loss and reconstruction losses. However, these methods do not impose any constraints on the latent space, resulting in intermediate features that are not suitable for clustering. Moreover, they suffer from poor clustering performance when the number of clusters is large. To address this problem, this paper proposes an autoencoder network with preclustered center codebooks for clustering, two codebooks to represent the cluster centers and center offsets, respectively, making the network features more compatible with the clustering task. Finally, We conducted experiments on CIFAR-10 and STL-10 datasets, the results indicate the effectiveness and superiority of the proposed network model.

关键词：

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：