检索结果-内蒙古大学图书馆

Maxwell’s Demon in MLP-Mixer:towards transferable adversarial attacks

Cybersecurity 2025年第1期8卷 180-188页

作者： Haoran Lyu Yajie Wang Yu‑an Tan Huipeng Zhou Yuhang Zhao Quanxin Zhang School of Cyberspace Science and Technology Beijing Institute of TechnologyBeijingChina School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina

Models based on MLP-Mixer architecture are becoming popular,but they still sufer from adversarial *** it has been shown that MLP-Mixer is more robust to adversarial attacks compared to convolutional neural networks(CNNs),there has been no research on adversarial attacks tailored to its *** this paper,we fll this *** propose a dedicated attack framework called Maxwell’s demon Attack(MA).Specifcally,we break the chan‑nel-mixing and token-mixing mechanisms of the MLP-Mixer by perturbing inputs of each Mixer layer to achieve high *** demonstrate that disrupting the MLP-Mixer’s capture of the main information of images by mask‑ing its inputs can generate adversarial examples with cross-architectural *** evaluations show the efectiveness and superior performance of *** generated based on masked inputs obtain a higher success rate of black-box attacks than existing transfer ***,our approach can be easily combined with existing methods to improve the transferability both within MLP-Mixer based models and to models with difer‑ent *** achieve up to 55.9%attack performance *** work exploits the true generaliza‑tion potential of the MLP-Mixer adversarial space and helps make it more robust for future deployments.

关键词： Adversarial attacks Adversarial examples Image classifcation

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based software engineering: progress,challenges, and opportunities

引用

science China(Information sciences) 2025年第1期68卷 57-144页

作者： Xiangping CHEN Xing HU Yuan HUANG He JIANG Weixing JI Yanjie JIANG Yanyan JIANG Bo LIU Hui LIU Xiaochen LI Xiaoli LIAN Guozhu MENG Xin PENG Hailong SUN Lin SHI Bo WANG Chong WANG Jiayi WANG Tiantian WANG Jifeng XUAN Xin XIA Yibiao YANG Yixin YANG Li ZHANG Yuming ZHOU Lu ZHANG School of Journalism and Communication Sun Yat-sen University School of Software Technology Zhejiang University School of Software Engineering Sun Yat-sen University School of Software Dalian University of Technology School of Computer Science and Technology Beijing Institute of Technology Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of EducationSchool of Computer Science Peking University State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering Beihang University Institute of Information Engineering Chinese Academy of Sciences School of Computer Science Fudan University State Key Laboratory of Complex & Critical Software Environment (CCSE) School of Software Beihang University School of Computer and Information Technology Beijing Jiaotong University School of Computer Science and Technology Harbin Institute of Technology School of Computer Science Wuhan University Huawei Technologies

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many studies have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However,although several surveys have provided overall pictures of the application of deep learning techniques in software engineering,they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this study, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas,we highlight the major advances achieved by applying deep learning techniques with pointers to the available datasets i

关键词： deep learning software engineering software benchmark software artifact representation survey

来源：评论

学校读者我要写书评

暂无评论

Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image

引用

Chinese Journal of Electronics 2024年第1期33卷 303-312页

作者： Tao ZHANG Ying FU Jun ZHANG School of Computer Science and Technology Beijing Institute of Technology Advanced Reasearch Institute of Multidisciplinary Science Beijing Institute of Technology

Denoising(DN) and demosaicing(DM) are the first crucial stages in the image signal processing pipeline. Recently, researches pay more attention to solve DN and DM in a joint manner, which is an extremely undetermined inverse problem. Existing deep learning methods learn the desired prior on synthetic dataset, which limits the generalization of learned network to the real world data. Moreover, existing methods mainly focus on the raw data property of high green information sampling rate for DM, but occasionally exploit the high intensity and signalto-noise(SNR) of green channel. In this work, a deep guided attention network(DGAN) is presented for real image joint DN and DM(JDD), which considers both high SNR and high sampling rate of green information for DN and DM, respectively. To ease the training and fully exploit the data property of green channel, we first train DN and DM sub-networks sequentially and then learn them jointly, which can alleviate the error accumulation. Besides, in order to support the real image JDD, we collect paired raw clean RGB and noisy mosaic images to conduct a realistic dataset. The experimental results on real JDD dataset show the presented approach performs better than the state-of-the-art methods, in terms of both quantitative metrics and qualitative visualization.

关键词： Image denoising Image demosaicing Joint processing Guided attention Paired real dataset

来源：评论

学校读者我要写书评

暂无评论

A Distributed Adaptive Second-Order Latent Factor Analysis Model

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2343-2345页

作者： Jialiang Wang Weiling Li Xin Luo the School of Computer Science and Technology Dongguan University of Technology the College of Computer and Information Science Southwest University

Dear Editor,This letter presents a distributed adaptive second-order latent factor(DAS) model for addressing the issue of high-dimensional and incomplete data representation. Compared with first-order optimizers, a second-order optimizer has stronger ability in approaching a better solution when dealing with the non-convex optimization problems, thus obtaining better performance in extracting the latent factors(LFs) well representing the known information from high-dimensional and incomplete data.

关键词： representation incomplete approaching

来源：评论

学校读者我要写书评

暂无评论

A Federated Learning Incentive Mechanism for Dynamic Client Participation:Unbiased Deep Learning Models

引用

computers, Materials & Continua 2025年第4期83卷 619-634页

作者： Jianfeng Lu Tao Huang Yuanai Xie Shuqin Cao Bing Li School of Computer Science and Technology Wuhan University of Science and TechnologyWuhan430065China College of Computer Science South-Central Minzu UniversityWuhan430074China School of Computer Science and Technology Zhejiang Normal UniversityJinhua321004China

The proliferation of deep learning(DL)has amplified the demand for processing large and complex datasets for tasks such as modeling,classification,and ***,traditional DL methods compromise client privacy by collecting sensitive data,underscoring the necessity for privacy-preserving solutions like Federated Learning(FL).FL effectively addresses escalating privacy concerns by facilitating collaborative model training without necessitating the sharing of raw *** that FL clients autonomously manage training data,encouraging client engagement is pivotal for successful model *** overcome challenges like unreliable communication and budget constraints,we present ENTIRE,a contract-based dynamic participation incentive mechanism for *** ensures impartial model training by tailoring participation levels and payments to accommodate diverse client *** approach involves several key ***,we examine how random client participation impacts FL convergence in non-convex scenarios,establishing the correlation between client participation levels and model ***,we reframe model performance optimization as an optimal contract design challenge to guide the distribution of rewards among clients with varying participation *** balancing budget considerations with model effectiveness,we craft optimal contracts for different budgetary constraints,prompting clients to disclose their participation preferences and select suitable contracts for contributing to model ***,we conduct a comprehensive experimental evaluation of ENTIRE using three real *** results demonstrate a significant 12.9%enhancement in model performance,validating its adherence to anticipated economic properties.

关键词： Federated learning deep learning non-IID data dynamic client participation non-convex optimization contract

来源：评论

学校读者我要写书评

暂无评论

Pushing the Limits of WiFi-Based Gait Recognition Towards Non-Gait Human Behaviors

引用

IEEE Transactions on Mobile Computing 2025年第07期24卷 6137-6153页

作者： Yan, Dawei Yang, Panlong Shang, Fei Han, Feiyu Yan, Yubo Li, Xiang-Yang University of Science and Technology of China School of Computer Science and Technology Hefei230021 China Nanjing University of Information Science & Technology School of Computer Science Nanjing210044 China

WiFi-based gait recognition technologies have seen significant advancements in recent years. However, most existing approaches rely on a critical assumption: users must walk continuously and maintain a consistent body posture. This poses a substantial challenge when users engage in non-periodic or discontinuous behaviors (e.g., stopping, starting, or turning mid-walk), which can disrupt the extraction of gait-related features and degrade recognition performance. To address this issue, we propose freeGait, a novel approach designed to mitigate the impact of non-gait behaviors in WiFi-based gait recognition systems. Our solution models this problem as domain adaptation, where we learn domain-independent representations to isolate gait features from behavior-dependent noise. We treat human behaviors with labeled user data as source domains and behaviors without user labels as target domains. However, applying domain adaptation directly is challenging due to the ambiguous classification boundaries in the target domains for WiFi signals. To overcome this, we align the posterior distributions between the source and target domains and constrain the conditional distribution within the target domains to enhance gait classification accuracy. Additionally, we implement a data augmentation module to generate data resembling the labeled data, while supervised learning ensures distinctiveness between users. Our experiments, conducted with 20 participants across 3 different scenarios, demonstrate that freeGait can accurately predict data across 15 domains by labeling only a small subset from 6 source domains, achieving up to a 45% improvement in user classification accuracy compared to existing methods. © 2025 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Optimizing B^(+)-tree for hybrid memory with in-node hotspot cache and eADR awareness

引用

Frontiers of computer science 2024年第5期18卷 133-145页

作者： Peiquan JIN Zhaole CHU Gaocong LIU Yongping LUO Shouhong WAN School of Computer Science and Technology University of Science and Technology of ChinaHefei 230027China

he advance in Non-Volatile Memory(NVM)has changed the traditional *** to DRAM,NVM has the advantages of nonvolatility and large ***,as the read/write speed of NVM is still lower than that of DRAM,building DRAM/NVM-based hybrid memory systems is a feasible way of adding NVM into the current computer *** paper aims to optimize the well-known B^(+)-tree for hybrid *** novelty of this study is ***,we observed that the space utilization of internal nodes in B^(+)-tree is generally below 70%.Inspired by this observation,we propose to maintain hot keys in the free space within internal nodes,yielding a new index named HATree(Hotness-Aware Tree).The new idea of HATree is to use the unused space of the parent of leaf nodes(PLNs)as the hotspot data ***,no extra space is needed,and the in-node hotspot cache can efficiently improve query ***,to further improve the update performance of HATree,we propose to utilize the eADR technology supported by the third-generation Intel Xeon Scalable Processors to enhance HATree with instant log persistence,which results in the new HATree-Log *** conduct extensive experiments on real hybrid memory architecture involving DRAM and Intel Optane Persistent Memory to evaluate the performance of HATree and *** state-of-the-art indices for hybrid memory,namely NBTree,LBTree,and FPTree,are included in the experiments,and the results suggest the efficiency of HATree and HATree-Log.

关键词： hybrid memory B^(+)-tree hotspot in-node cache eADR

来源：评论

学校读者我要写书评

暂无评论

Task-specific Part Discovery for Fine-grained Few-shot Classification

引用

Machine Intelligence Research 2024年第5期21卷 954-965页

作者： Yongxian Wei Xiu-Shen Wei School of Computer Science and Technology Nanjing University of Science and TechnologyNanjing210094China

Localizing discriminative object parts(e.g.,bird head)is crucial for fine-grained classification tasks,especially for the more challenging fine-grained few-shot *** work always relies on the learned object parts in a unified manner,where they attend the same object parts(even with common attention weights)for different few-shot episodic *** this paper,we propose that it should adaptively capture the task-specific object parts that require attention for each few-shot task,since the parts that can distinguish different tasks are naturally *** for a few-shot task,after obtaining part-level deep features,we learn a task-specific part-based dictionary for both aligning and reweighting part features in an ***,part-level categorical prototypes are generated based on the part features of support data,which are later employed by calculating distances to classify query data for *** retain the discriminative ability of the part-level representations(i.e.,part features and part prototypes),we design an optimal transport solution that also utilizes query data in a transductive way to optimize the aforementioned distance calculation for the final *** experiments on five fine-grained benchmarks show the superiority of our method,especially for the 1-shot setting,gaining 0.12%,8.56%and 5.87%improvements over state-of-the-art methods on CUB,Stanford Dogs,and Stanford Cars,respectively.

关键词： Fine-grained image recognition few-shot learning transductive learning visual dictionary part feature discovery

来源：评论

学校读者我要写书评

暂无评论

Using DTL-MD with GANs and ResNet for Malicious Code Detection

引用

Informatica (Slovenia) 2025年第14期49卷 63-78页

作者： Li, Yiming Xie, Tao Mei, Dongdong Department of Computer Science and Technology School of Computer Science and Engineering Ningxia Institute of Science and Technology Shizuishan753000 China

This study proposes a malicious code detection model DTL-MD based on deep transfer learning, which aims to improve the detection accuracy of existing methods in complex malicious code and data scarcity. In the feature extraction process, the weighted sum method of GIST and LBP features is used to combine the advantages of the two features. Online transfer learning is used to reduce the data distribution difference between the target domain and the source domain. The model uses ResNet50V2 as the backbone network and combines SimAM to enhance the feature extraction and representation capabilities. In addition, in order to further improve the robustness of detection, GAN is used to generate malicious code variants and expand the training data set. In the experiment, the public CICIDS 2017 data set is used for model training and testing. The performance test results show that when the threshold is 0.7, the accuracy of DTL-MD is 95.8% and the F1 score is 0.93. In a performance test involving 30,000 samples, the throughput of the DTL-MD model under Trojans, viruses, worms, and adware is 11, 12, 11, and 12 tasks/s, respectively, and the inference time is 211, 225, 239, and 234 samples/s, respectively. Compared with GAN, DTL-MD increases the throughput by about 10% and the inference speed by about 15%. The research aims to provide new ideas for improving the intelligence and automation level of malicious code detection technology, which has certain application value and practical significance. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Control for Discrete-Time Markov Jump Systems with Multi-Node Round-Robin Protocol

引用

IAENG International Journal of Applied Mathematics 2025年第1期55卷 126-133页

作者： Fang, Qi He, Lanlan Liu, Jie Jiang, Taiping School of Computer Science and Technology Anhui University of Technology Ma'anshan243032 China School of Computer Science and Technology Anhui University of Technology Ma'anshan243032 China School of Computer Science and Technology Anhui University of Technology Ma'anshan243032 China School of Computer Science and Technology Anhui University of Technology Ma'anshan243032 China

This paper considers the asynchronous control for discrete-time Markov jump systems (MJSs) using a multi-node round-robin protocol (MNRRP). Compared to the traditional round-robin protocol, MNRRP increases the number of nodes updated at each transmission time, thereby improving system performance. In addition, a hidden Markov model is constructed to address the asynchronous behavior between the controlled object and the controller. Using Lyapunov functions and several inequalities, a criterion is provided to ensure the stochastic stability of MJS and joint L2 – L1 and H1 performance. A required asynchronous controller design approach is then presented based on the scheduling signal. Finally, a numerical example is given to verify the feasibility and applicability of the theoretical results. © (2025), (International Association of Engineers). All rights reserved.

关键词： Hidden Markov models

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：