检索结果-内蒙古大学图书馆

TSGN: Transaction Subgraph Networks Assisting Phishing Detection in Ethereum

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wang, Jinhuan Chen, Pengtao Xu, Xinyao Wu, Jiajing Shen, Meng Xuan, Qi Yang, Xiaoniu Zhejiang University of Technology Institute of Cyberspace Security College of Information Engineering Hangzhou310023 China ZJUT Binjiang Institute of Artificial Intelligence Hangzhou310056 China Fudan University Adaptive Networks and Control Lab Department of Electronic Engineering School of Information Science and Technology Shanghai200433 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Shenzhen518066 China National Key Laboratory of Electromagnetic Space Security Jiaxing314033 China

Due to the decentralized and public nature of the blockchain ecosystem, malicious activities on the Ethereum platform impose immeasurable losses on users. At the same time, the transparency of cryptocurrency transactions provides a unique opportunity to analyze illegal activities, such as phishing scams, from a network perspective. Most existing phishing scam detection methods focus primarily on analyzing account interaction networks, which limits their ability to uncover transaction behavior patterns embedded within transaction interactions. To address this, we construct the Transaction SubGraph Network (TSGN) by using transaction subgraphs as basic elements and further propose a novel framework for Ethereum phishing account detection. Specifically, we rebuild the graph structures via three well-designed mapping mechanisms, yielding TSGN and its two variants, i.e., Directed-TSGN and Temporal-TSGN, to obtain direction-aware and time-aware transfer flow features. By further incorporating the mapping strategy into transaction multidigraphs, we develop the Multiple-TSGN, which could preserve more transaction flow features while concurrently reducing the time consumption of modeling large-scale networks. TSGN models based on transaction subgraph interactions can capture complex higher-order dependencies, which lay beyond the reach of models that exclusively capture pairwise account interactions. As a general framework, our model can incorporate various feature extraction methods to improve the performance of phishing detection. Extensive experimental results on Ethereum datasets show that our method achieves superior performance in phishing detection, yielding 3.27%∼6.71% relative improvement over previous state-of-the-art. © 2004-2012 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Dunhuang murals image inpainting method based on fusion classification pre-training model

Dunhuang murals image inpainting method based on fusion clas...

引用

Culture-Oriented science and technology (CoST), International Conference on

作者： Hui Ren Chengya Zhang Ke Sun Chenyu Ye School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Audiovisual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China Beijing Key Laboratory of Modern Performing Arts Technology Beijing China School of Engineering and Applied Science University of Pennsylvania PA USA

ISBN: (数字)9798350380347

ISBN: (纸本)9798350380354

Murals are an important part of China’s cultural heritage. Because of their age, Dunhuang murals have suffered from discoloration, fading and damage. With the development of computer image restoration technology, digital image processing provides strong support for mural restoration. Although there are many research results in the field of ancient mural images, there is no pre-trained model based on ancient mural images available for migration. There is a method for Dunhuang murals image restoration based on Generative Adversarial Network (GAN) with improved ResNet50 structure as an encoder in the generator. This research result proposes a generative adversarial network model with a parallel double convolutional extraction of deep features for the generator, combined with a ternary heterogeneous joint discriminator. On this basis, this paper proposes a binary classification task to distinguish ancient mural images from modern natural style images, so that the model pre-learns features such as color, texture, and structure of mural images, which are inputted into the restoration network as a priori information, in order to achieve the effect of reducing the probability of incomplete restoration of the model, and better generalization ability. The experimental results show that the method proposed in this paper has an overall improvement in the evaluation indexes such as Peak Signal to Noise Ratio(PSNR) and Structural Similarities(SSIM) when compared with other methods, and the restored images are more in line with human subjective vision, which proves the validity of the method.

关键词： Training Uncertainty Noise Maintenance engineering Generative adversarial networks Feature extraction Generators

来源：评论

学校读者我要写书评

暂无评论

DarkFed: A Data-Free Backdoor Attack in Federated Learning

arXiv

引用

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

A Note on Basis of Lattice and Successive Minimal Vectors

SSRN

引用

SSRN 2024年

作者： Zhu, Chaoxi Zhao, Wei Zhao, Jianrong Zhou, Zhengchun National Key Laboratory of Security Communication Chengdu610041 China School of Economic Mathematics Southwestern University of Finance and Economics Chengdu610074 China School of Information Science and Technology Southwest Jiaotong University Chengdu610031 China

Let L ∈ 2 be a lattice of 2-dimension. The conclusion "the shortest vector s1 (under the supremum norm) in L\{0} and the second shortest vector s2 (the shortest vector in L\{ns1|n ∈ }) form a base of L" is widely used. In this note, we find this conclusion is slightly flawed. Let c be a nonzero real number. We prove that the above conclusion is true except that L = {c(n1, n2)|n1, n2 ∈ } with {s1, s2} ⊆ {(c, c), (−c, −c), (c, −c), (−c, c)}, in which case s1 and s2 don’t form a base of L although s1 and s2 are successive minimal vectors of L under the supremum norm. © 2024, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Multi-view infrared small target recognition based on YOLOv5

Multi-view infrared small target recognition based on YOLOv5

引用

Chinese Automation Congress (CAC)

作者： Hua Gong Shasha Liu Song Guan Kuaikuai Yu Fang Liu College of Science Shengyang Ligong University Shenyang China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjing China

In order to improve the recognition accuracy of small infrared targets in complex environment, a SyluInfrared dataset is built by taking multi-view infrared images with the Frock TiX600 infrared thermal imager. Seven image enhancement algorithms including image brightening, contrast adjustment, image blurring, image flipping and image scaling are designed to improve the image quality of small infrared targets. The YOLOv5 deep learning model is used to identify small infrared targets with multiple views to improve the recognition accuracy of small infrared targets. The experimental results show that the accuracy of multi-view infrared small target recognition model for YOLOv5 deep network is 97.7%, which is 6.6% higher than that of single-view infrared small target recognition model based on YOLOv5. The multi-view target recognition strategy significantly improves the infrared small target recognition performance.

关键词： Image quality Deep learning Image recognition Automation Target recognition Object detection Data models

来源：评论

学校读者我要写书评

暂无评论

Joint Computation Offloading and Resource Allocation for LEO Satellite Networks Using Hierarchical Multi-Agent Reinforcement Learning

引用

IEEE Transactions on Cognitive communications and Networking 2024年

作者： Lai, Junyu Liu, Huashuo Xu, Guoyao Jiang, Weiwei Wang, Xiong Jiang, Dingde University of Electronic Science and Technology of China School of Aeronautics and Astronautics China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China University of Electronic Science and Technology of China School of Aeronautics and Astronautics Chengdu611731 China Ministry of Education Key Laboratory of Universal Wireless Communications China Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing100876 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China

The integration of edge computing with LEO satellite broadband networks (LSBNs) offers a transformative potential, yet remains underexplored in the optimization of joint computation offloading and resource allocation (JCORA). This problem is compounded by the issues of load imbalance and hybrid action spaces. To tackle them, we firstly propose a multi-level edge computing architecture that leverages the inter-satellite links to enable collaborative offloading among neighboring satellites, thereby enhancing global resource utilization and load balance in LSBNs. Moreover, existing studies demonstrate the benefits of deep reinforcement learning (DRL) for JCORA optimization but struggle with the complexities of hybrid action spaces. To address this, we elaborate a novel hierarchical multi-agent DRL (HMADRL) framework that decomposes the JCORA problem into two-layered subproblems, namely global computation offloading and local resource allocation. This decomposition effectively mitigates the challenge posed by hybrid action spaces. The computation offloading subproblem is formulated as a delayed-reward partially observable Markov decision process, optimized by using multi-agent deep Q-networks specialized in discrete action outputs. Meanwhile, the resource allocation subproblem is addressed through the deep deterministic policy gradient model, adept at handling continuous actions. Extensive experiments validate our approach, demonstrating improvements in delay reduction, outrage rate, and load balancing compared to baselines. © 2015 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Infrared Target Detection Based on the Fusion of Mask R-CNN and Image Enhancement Network

Infrared Target Detection Based on the Fusion of Mask R-CNN ...

引用

Chinese Automation Congress (CAC)

作者： Fang Liu Song Guan Kuaikuai Yu Hua Gong College of Science Shengyang Ligong University Shenyang China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjing China

In this paper, we focus on the problem of the infrared image detection. Aiming at the problem of the low contrast of the infrared images, an adaptive gamma transformation algorithm (AGT) is established to intelligently improve the contrast of the infrared images. Aiming at the problem of the weak edge information of the infrared images, an improved Sobel operator edge enhancement algorithm (ISOEE) is designed to enrich the edge features of the infrared images. In order to solve the problem that the traditional infrared image detection algorithm relies on expert experience, the fusion infrared images detection model AIE-Mask R-CNN based on Mask R-CNN, AGT algorithm and ISOEE algorithm is proposed. This fusion model can realize accurate and intelligent detection for the infrared images. The experimental results show that the fusion model AIE-Mask R-CNN improves the detection accuracy of the infrared images.

关键词： Adaptation models Automation Image edge detection Object detection Detection algorithms Image enhancement

来源：评论

学校读者我要写书评

暂无评论

IoT ETEI: End-to-End IoT Device Identification Method

IoT ETEI: End-to-End IoT Device Identification Method

引用

IEEE Conference on Dependable and Secure Computing

作者： Feihong Yin Li Yang Yuchen Wang Jiahao Dai Xidian University Xi'an China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

ISBN: (数字)9781728175348

ISBN: (纸本)9781728175355

The past decades have seen the rapid development of Internet of Things (IoT) in various domains. Identifying the IoT devices connected to the network is a crucial aspect of network security. However, existing work on identifying IoT devices based on manually extracted features and prior knowledge, leading to low efficiency and identification accuracy. In this paper, we propose an automatic end-to-end IoT device identification method (IoT ETEI) based on CNN+BiLSTM deep learning model, which outperforms traditional methods from the perspective of overhead and identify accuracy. We demonstrate the effectiveness and flexibility of the proposed method by deploying IoT ETEI in the face of identifying IoT devices on public datasets with the accuracy rate over 99 %, even for IoT devices that use encryption protocols.

关键词： Deep learning Telecommunication traffic Feature extraction Encryption Object recognition Internet of Things security

来源：评论

学校读者我要写书评

暂无评论

Semi-LDPC Convolutional Codes:Construction and Low-Latency Windowed List Decoding

引用

Journal of communications and information Networks 2021年第4期6卷 411-419页

作者： Qianfan Wang Suihua Cai Li Chen Xiao Ma School of Electronics and Communication Engineering Sun Yat-sen UniversityGuangzhou 510006China School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen UniversityGuangzhou 510006China School of Electronics and Information Technology Sun Yat-sen UniversityGuangzhou 510006China

This paper presents a new coding scheme called semi-low-density parity-check convolutional code(semi-LDPC-CC),whose parity-check matrix consists of both sparse and dense sub-matrices,a feature distinguished from the conventional *** propose sliding-window list(SWL)decoding algorithms with a fixed window size of two,resulting in a low decoding latency but a competitive error-correcting *** performance can be predicted by upper bounds derived from the first event error probability and by genie-aided(GA)lower bounds estimated from the underlying LDPC block codes(LDPC-BCs),while the complexity can be reduced by truncating the list with a threshold on the difference between the soft metrics in the serial decoding *** results are presented to validate our analysis and demonstrate the performance advantage of the semi-LDPC-CCs over the conventional LDPC-CCs.

关键词： low-density parity-check convolutional codes(LDPC-CCs) spatially coupled LDPC(SC-LDPC)codes sliding-window list(SWL)decoding

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：