Tsinghua Science and Technology最新文献_第4页

Minimizing Age of Information in UAV-Assisted Edge Computing System with Multiple Transmission Modes 多传输模式下无人机辅助边缘计算系统信息年龄最小化

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2024.9010046

Yanhua Pei;Yunzhi Zhao;Fen Hou

{"title":"Minimizing Age of Information in UAV-Assisted Edge Computing System with Multiple Transmission Modes","authors":"Yanhua Pei;Yunzhi Zhao;Fen Hou","doi":"10.26599/TST.2024.9010046","DOIUrl":"https://doi.org/10.26599/TST.2024.9010046","url":null,"abstract":"With the advance of 5G technologies and the development of space-air-ground-sea applications, the fast and efficient collection and processing of the explosive growth of sensing data have become significant and challenging. In this paper, considering the Age of Information (AoI), the limited coverage of Base Stations (BS), and the constrained computation capability of Unmanned Aerial Vehicle (UAV), we propose a hybrid communication framework that utilizes UAVs as relays to optimize the collection of sensing data. We aim to minimize the average AoI of the data among all sensor nodes while considering the energy consumption constraints of sensor nodes, which is formulated as a Mixed Integer NonLinear Programming (MINLP). To address this problem, we decompose it into communication resource allocation and computation resource allocation. Finally, the average AoI of the whole system is minimized and the average energy consumption constraint of sensor nodes is satisfied. The simulation results show that our proposed method can achieve significant performance improvement. In specific, our proposed method can reduce the average AoI by 20%, 11%, and 43% compared to the three counterparts, Data Transmission Directly Algorithm (DTDA), Max Weight Algorithm (MWA), and matching algorithm, respectively.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1060-1078"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817717","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fake News Detection: Extendable to Global Heterogeneous Graph Attention Network with External Knowledge 假新闻检测：可扩展到具有外部知识的全局异构图注意网络

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2023.9010104

Yihao Guo;Longye Qiao;Zhixiong Yang;Jianping Xiang;Xinlong Feng;Hongbing Ma

{"title":"Fake News Detection: Extendable to Global Heterogeneous Graph Attention Network with External Knowledge","authors":"Yihao Guo;Longye Qiao;Zhixiong Yang;Jianping Xiang;Xinlong Feng;Hongbing Ma","doi":"10.26599/TST.2023.9010104","DOIUrl":"https://doi.org/10.26599/TST.2023.9010104","url":null,"abstract":"Distinguishing genuine news from false information is crucial in today's digital era. Most of the existing methods are based on either the traditional neural network sequence model or graph neural network model that has become more popularity in recent years. Among these two types of models, the latter solve the former's problem of neglecting the correlation among news sentences. However, one layer of the graph neural network only considers the information of nodes directly connected to the current nodes and omits the important information carried by distant nodes. As such, this study proposes the Extendable-to-Global Heterogeneous Graph Attention network (namely EGHGAT) to manage heterogeneous graphs by cleverly extending local attention to global attention and addressing the drawback of local attention that can only collect information from directly connected nodes. The shortest distance matrix is computed among all nodes on the graph. Specifically, the shortest distance information is used to enable the current nodes to aggregate information from more distant nodes by considering the influence of different node types on the current nodes in the current network layer. This mechanism highlights the importance of directly or indirectly connected nodes and the effect of different node types on the current nodes, which can substantially enhance the performance of the model. Information from an external knowledge base is used to compare the contextual entity representation with the entity representation of the corresponding knowledge base to capture its consistency with news content. Experimental results from the benchmark dataset reveal that the proposed model significantly outperforms the state-of-the-art approach. Our code is publicly available at https://github.com/gyhhk/EGHGAT_FakeNewsDetection.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1125-1138"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817715","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI-Enabled STAR-RIS Aided MISO ISAC Secure Communications 启用人工智能的星- ris辅助MISO ISAC安全通信

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2024.9010086

Zhengyu Zhu;Mengfei Gong;Gangcan Sun;Peijia Liu;De Mi

{"title":"AI-Enabled STAR-RIS Aided MISO ISAC Secure Communications","authors":"Zhengyu Zhu;Mengfei Gong;Gangcan Sun;Peijia Liu;De Mi","doi":"10.26599/TST.2024.9010086","DOIUrl":"https://doi.org/10.26599/TST.2024.9010086","url":null,"abstract":"A simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) aided integrated sensing and communication (ISAC) dual-secure communication system is studied in this paper. The sensed target and legitimate users (LUs) are situated on the opposite sides of the STAR-RIS, and the energy splitting and time switching protocols are applied in the STAR-RIS, respectively. The long-term average security rate for LUs is maximized by the joint design of the base station (BS) transmit beamforming and receive filter, along with the STAR-RIS transmitting and reflecting coefficients, under guarantying the echo signal-to-noise ratio thresholds and rate constraints for the LUs. Since the channel information changes over time, conventional convex optimization techniques cannot provide the optimal performance for the system, and result in excessively high computational complexity in the exploration of the long-term gains for the system. Taking continuity control decisions into account, the deep deterministic policy gradient and soft actor-critic algorithms based on off-policy are applied to address the complex non-convex problem. Simulation results comprehensively evaluate the performance of the proposed two reinforcement learning algorithms and demonstrate that STAR-RIS is remarkably better than the two benchmarks in the ISAC system.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"998-1011"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817769","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A First Successful Factorization of RSA-2048 Integer by D-Wave Quantum Computer 用d波量子计算机首次成功分解RSA-2048整数

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2024.9010028

Chao Wang;Jingjing Yu;Zhi Pei;Qidi Wang;Chunlei Hong

{"title":"A First Successful Factorization of RSA-2048 Integer by D-Wave Quantum Computer","authors":"Chao Wang;Jingjing Yu;Zhi Pei;Qidi Wang;Chunlei Hong","doi":"10.26599/TST.2024.9010028","DOIUrl":"https://doi.org/10.26599/TST.2024.9010028","url":null,"abstract":"Integer factorization, the core of the Rivest-Shamir-Adleman (RSA) attack, is an exciting but formidable challenge. As of this year, a group of researchers' latest quantum supremacy chip remains unavailable for cryptanalysis. Quantum annealing (QA) has a unique quantum tunneling advantage, which can escape local extremum in the exponential solution space, finding the global optimal solution with a higher probability. Consequently, we consider it an effective method for attacking cryptography. According to Origin Quantum Computing, QA computers are able to factor numbers several orders of magnitude larger than universal quantum computers. We try to transform the integer factorization problem in RSA attacks into a combinatorial optimization problem by using the QA algorithm of D-Wave quantum computer, and attack RSA-2048 which is composed of a class of special integers. The experiment factored this class of integers of size 2\u0000<sup>2048</sup>\u0000, \u0000<tex>$N=ptimes q$</tex>\u0000 As an example, the article gives the results of 10 RSA-2048 attacks in the appendix. This marks the first successful factorization of RSA-2048 by D-Wave quantum computer, regardless of employing mathematical or quantum techniques, despite dealing with special integers, exceeding 2\u0000<sup>1061</sup>\u0000−1 of California State University. This experiment verifies that the QA algorithm based on D-Wave is an effective method to attack RSA.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1270-1282"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817698","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High Capacity Reversible Data Hiding Algorithm in Encrypted Images Based on Image Adaptive MSB Prediction and Secret Sharing 基于图像自适应MSB预测和秘密共享的加密图像高容量可逆数据隐藏算法

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2023.9010116

Kaili Qi;Minqing Zhang;Fuqiang Di;Chao Jiang

{"title":"High Capacity Reversible Data Hiding Algorithm in Encrypted Images Based on Image Adaptive MSB Prediction and Secret Sharing","authors":"Kaili Qi;Minqing Zhang;Fuqiang Di;Chao Jiang","doi":"10.26599/TST.2023.9010116","DOIUrl":"https://doi.org/10.26599/TST.2023.9010116","url":null,"abstract":"Until now, some reversible data hiding in encrypted images (RDH-EI) schemes based on secret sharing (SIS-RDHEI) still have the problems of not realizing diffusivity and high embedding capacity. Therefore, this paper innovatively proposes a high capacity RDH-EI scheme that combines adaptive most significant bit (MSB) prediction with secret sharing technology. Firstly, adaptive MSB prediction is performed on the original image and cryptographic feedback secret sharing strategy encrypts the spliced pixels to spare embedding space. In the data hiding phase, each encrypted image is sent to a data hider to embed the secret information independently. When \u0000<tex>$r$</tex>\u0000 copies of the image carrying the secret text are collected, the original image can be recovered lossless and the secret information can be extracted. Performance evaluation shows that the proposed method in this paper has the diffusivity, reversibility, and separability. The last but the most important, it has higher embedding capacity. For \u0000<tex>$512 times 515$</tex>\u0000 grayscale images, the average embedding rate reaches 4.7358 bits per pixel (bpp). Compared to the average embedding rate that can be achieved by the Wang et al.'s SIS-RDHEI scheme, the proposed scheme with (2, 2), (2, 3), (2, 4), (3, 4), and (3, 5)-threshold can increase by 0.7358 bpp, 2.0658 bpp, 2.7358 bpp, 0.7358 bpp, and 1.5358 bpp, respectively.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1139-1156"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817719","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Influencing Factors Landslide Susceptibility Prediction Model Based on Monte Carlo Neural Network 基于蒙特卡罗神经网络的多影响因素滑坡易感性预测模型

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2023.9010115

Hongtao Zhang;Qingguo Zhou

{"title":"Multi-Influencing Factors Landslide Susceptibility Prediction Model Based on Monte Carlo Neural Network","authors":"Hongtao Zhang;Qingguo Zhou","doi":"10.26599/TST.2023.9010115","DOIUrl":"https://doi.org/10.26599/TST.2023.9010115","url":null,"abstract":"Geological hazard risk assessment and severity prediction are of great significance for disaster prevention and mitigation. Traditional methods require a long time to evaluate and rely heavily on human experience. Therefore, based on the key factors affecting landslides, this paper designs a geological disaster prediction model based on Monte Carlo neural network (MCNN). Firstly, based on the weights of evidence method, a correlation analysis was conducted on common factors affecting landslides, and several key factors that have the greatest impact on landslide disasters, including geological lithology, slope gradient, slope type, and rainfall, were identified. Then, based on the monitoring data of Lanzhou City, 18 367 data records were collected and collated to form a dataset. Subsequently, these multiple key influencing factors were used as inputs to train and test the landslide disaster prediction model based on MCNN. After determining the hyperparameters of the model, the training and prediction capabilities of the model were evaluated. Through comparison with several other artificial intelligence models, it was found that the prediction accuracy of the model studied in this paper reached 89%, and the Macro-Precision, Macro-Recall, and Macro-F1 indicators were also higher than other models. The area under curve (AUC) index reached 0.8755, higher than the AUC value based on a single influencing factor in traditional methods. Overall, the method studied in this paper has strong predictive ability and can provide certain decision support for relevant departments.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1215-1228"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817721","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advanced Deep Neural Network with Unified Feature-Aware and Label Embedding for Multi-Label Arrhythmias Classification 基于统一特征感知和标签嵌入的高级深度神经网络多标签心律失常分类

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2023.9010162

Pan Xia;Zhongrui Bai;Yicheng Yao;Lirui Xu;Hao Zhang;Lidong Du;Xianxiang Chen;Qiao Ye;Yusi Zhu;Peng Wang;Xiaoran Li;Guangyun Wang;Zhen Fang

{"title":"Advanced Deep Neural Network with Unified Feature-Aware and Label Embedding for Multi-Label Arrhythmias Classification","authors":"Pan Xia;Zhongrui Bai;Yicheng Yao;Lirui Xu;Hao Zhang;Lidong Du;Xianxiang Chen;Qiao Ye;Yusi Zhu;Peng Wang;Xiaoran Li;Guangyun Wang;Zhen Fang","doi":"10.26599/TST.2023.9010162","DOIUrl":"https://doi.org/10.26599/TST.2023.9010162","url":null,"abstract":"Multi-label arrhythmias classification is of great significance to the diagnosis of cardiovascular disease, and it is a challenging task as it requires identifying the label subset most related to each instance. In this paper, by integrating a deep residual neural network and auto-encoder, we propose an advanced deep neural network (DNN) framework with unified feature-aware and label embedding to perform multi-label arrhythmias classification involving 30 types of arrhythmias. Firstly, a deep residual neural network is built to extract the complex pathological features from varying-dimensional electrocardiograms (ECGs). Secondly, the mean square error loss is adopted to learn a latent space associating the deep pathological features and the corresponding label data, and then to achieve unified feature-label embedding. Thirdly, the label-correlation aware loss is introduced to optimize the auto-encoder architecture, which enables our model to exploit label-correlation for improved multi-label prediction. Our proposed DNN model can allow end-to-end training and prediction, which can perform feature-aware, label embedding, and label-correlation aware prediction in a unified framework. Finally, our proposed model is evaluated on the currently largest public dataset worldwide, and achieves the challenge metric scores of 0.492, 0.495, and 0.490 on the 12-lead, 3-lead, and all-lead version ECGs, respectively. The performance of our approach outperforms other current state-of-the-art methods in the leave-one-dataset-out cross-validation setting, which demonstrates that our approach has great competitiveness in identifying a wider range of multi-label arrhythmias.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1251-1269"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817700","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AMTrans: Auto-Correlation Multi-Head Attention Transformer for Infrared Spectral Deconvolution 红外光谱反褶积自相关多头注意转换器

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2024.9010131

Lei Gao;Liyuan Cui;Shuwen Chen;Lizhen Deng;Xiaokang Wang;Xiaohong Yan;Hu Zhu

{"title":"AMTrans: Auto-Correlation Multi-Head Attention Transformer for Infrared Spectral Deconvolution","authors":"Lei Gao;Liyuan Cui;Shuwen Chen;Lizhen Deng;Xiaokang Wang;Xiaohong Yan;Hu Zhu","doi":"10.26599/TST.2024.9010131","DOIUrl":"https://doi.org/10.26599/TST.2024.9010131","url":null,"abstract":"Infrared spectroscopy analysis has found widespread applications in various fields due to advancements in technology and industry convergence. To improve the quality and reliability of infrared spectroscopy signals, deconvolution is a crucial preprocessing step. Inspired by the transformer model, we propose an Auto-correlation Multi-head attention Transformer (AMTrans) for infrared spectrum sequence deconvolution. The auto-correlation attention model improves the scaled dot-product attention in the transformer. It utilizes attention mechanism for feature extraction and implements attention computation using the auto-correlation function. The auto-correlation attention model is used to exploit the inherent sequence nature of spectral data and to effectively recovery spectra by capturing auto-correlation patterns in the sequence. The proposed model is trained using supervised learning and demonstrates promising results in infrared spectroscopic restoration. By comparing the experiments with other deconvolution techniques, the experimental results show that the method has excellent deconvolution performance and can effectively recover the texture details of the infrared spectrum.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1329-1341"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817762","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Fine-Grained Image Classification Model Based on Hybrid Attention and Pyramidal Convolution 基于混合注意力和金字塔卷积的细粒度图像分类模型

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2024.9010025

Sifeng Wang;Shengxiang Li;Anran Li;Zhaoan Dong;Guangshun Li;Chao Yan

{"title":"A Fine-Grained Image Classification Model Based on Hybrid Attention and Pyramidal Convolution","authors":"Sifeng Wang;Shengxiang Li;Anran Li;Zhaoan Dong;Guangshun Li;Chao Yan","doi":"10.26599/TST.2024.9010025","DOIUrl":"https://doi.org/10.26599/TST.2024.9010025","url":null,"abstract":"Finding more specific subcategories within a larger category is the goal of fine-grained image classification (FGIC), and the key is to find local discriminative regions of visual features. Most existing methods use traditional convolutional operations to achieve fine-grained image classification. However, traditional convolution cannot extract multi-scale features of an image and existing methods are susceptible to interference from image background information. Therefore, to address the above problems, this paper proposes an FGIC model (Attention-PCNN) based on hybrid attention mechanism and pyramidal convolution. The model feeds the multi-scale features extracted by the pyramidal convolutional neural network into two branches capturing global and local information respectively. In particular, a hybrid attention mechanism is added to the branch capturing global information in order to reduce the interference of image background information and make the model pay more attention to the target region with fine-grained features. In addition, the mutual-channel loss (MC-LOSS) is introduced in the local information branch to capture fine-grained features. We evaluated the model on three publicly available datasets CUB-200-2011, Stanford Cars, FGVC-Aircraft, etc. Compared to the state-of-the-art methods, the results show that Attention-PCNN performs better.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1283-1293"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817763","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adversarial Attack on Object Detection via Object Feature-Wise Attention and Perturbation Extraction 基于目标特征关注和扰动提取的目标检测对抗攻击

IF 6.6 1区计算机科学

Tsinghua Science and Technology Pub Date : 2024-12-30 DOI: 10.26599/TST.2024.9010029

Wei Xue;Xiaoyan Xia;Pengcheng Wan;Ping Zhong;Xiao Zheng

{"title":"Adversarial Attack on Object Detection via Object Feature-Wise Attention and Perturbation Extraction","authors":"Wei Xue;Xiaoyan Xia;Pengcheng Wan;Ping Zhong;Xiao Zheng","doi":"10.26599/TST.2024.9010029","DOIUrl":"https://doi.org/10.26599/TST.2024.9010029","url":null,"abstract":"Deep neural networks are commonly used in computer vision tasks, but they are vulnerable to adversarial samples, resulting in poor recognition accuracy. Although traditional algorithms that craft adversarial samples have been effective in attacking classification models, the attacking performance degrades when facing object detection models with more complex structures. To address this issue better, in this paper we first analyze the mechanism of multi-scale feature extraction of object detection models, and then by constructing the object feature-wise attention module and the perturbation extraction module, a novel adversarial sample generation algorithm for attacking detection models is proposed. Specifically, in the first module, based on the multi-scale feature map, we reduce the range of perturbation and improve the stealthiness of adversarial samples by computing the noise distribution in the object region. Then in the second module, we feed the noise distribution into the generative adversarial networks to generate adversarial perturbation with strong attack transferability. By doing so, the proposed approach possesses the ability to better confuse the judgment of detection models. Experiments carried out on the DroneVehicle dataset show that our method is computationally efficient and works well in attacking detection models measured by qualitative analysis and quantitative analysis.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 3","pages":"1174-1189"},"PeriodicalIF":6.6,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817718","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0