检索结果-内蒙古大学图书馆

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

作者： Wei Wan Yuxuan Ning Shengshan Hu Lulu Xue Minghui Li Leo Yu Zhang Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security 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 Cluster and Grid Computing Lab

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of *** this paper, we present a novel poisoning attack known as $\color{Fuchsia} {{\text{MISA}}}$. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

Why Does Little Robustness Help? A Further Step Towards Unde...

引用

IEEE Symposium on Security and Privacy

作者： Yechao Zhang Shengshan Hu Leo Yu Zhang Junyu Shi Minghui Li Xiaogeng Liu Wei Wan Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University School of Software Engineering Huazhong University of Science and Technology Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

Adversarial examples for deep neural networks (DNNs) are transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical *** this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient *** on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifests in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other, and emphasize the

关键词： Training Privacy Buildings Closed box Minimization Data augmentation Robustness

来源：评论

学校读者我要写书评

暂无评论

Neutral Current Suppression for a Common Mode Decoupling Three-phase Transformerless Converter 5

Neutral Current Suppression for a Common Mode Decoupling Thr...

引用

5th IEEE Conference on Energy Internet and Energy system Integration, EI2 2021

作者： Cui, Xuan Xu, Shan Wang, Lei Zhang, Xinfang Zhang, Baifu Shanxi Key Laboratory of Power System Operation and Control Taiyuan University of Technology Taiyuan China Information and Communication Branch of Hebei Electric Power Co. Ltd. State Grid Corporation Shijiazhuang China

ISBN: (纸本)9781665434256

An independently controlled neutral module (ICNM) can be adopted in common mode decoupling three-phase transformerless AC-DC converter. When the load is unbalanced, the neutral line can provide a path for the zero sequence current. The initial control goal of ICNM is to stabilize the neutral voltage. Due to the phase jump of [-180] ° at the resonant frequency of the neutral inductance in the system loop gain and the split DC bus capacitor, the system may be unstable. In order to ensure system stability, inductive current feedback scheme (ICFS) can be adopted. Firstly, the equivalent circuit and basic control method of ICNM are proposed in this paper. Then, the stability of the original control is analyzed. Finally, an ICFS method to improve system stability is proposed.. © 2021 IEEE

关键词： system stability

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Surgery: Towards Accurate and Efficient Multi-Exit Networks

arXiv

引用

arXiv 2024年

作者： Gong, Cheng Chen, Yao Luo, Qiuyang Lu, Ye Li, Tao Zhang, Yuzhi Sun, Yufei Zhang, Le College of Software Nankai University China College of Computer Science Nankai University China National University of Singapore Singapore School of Information and Communication Engineering University of Electronic Science and Technology of China China HAIHE Lab of ITAI China Tianjin Key Laboratory of Network and Data Security Technology China Key Laboratory of Data and Intelligent System Security Ministry of Education

Multi-exit network is a promising architecture for efficient model inference by sharing backbone networks and weights among multiple exits. However, the gradient conflict of the shared weights results in sub-optimal accuracy. This paper introduces Deep Feature Surgery (DFS), which consists of feature partitioning and feature referencing approaches to resolve gradient conflict issues during the training of multi-exit networks. The feature partitioning separates shared features along the depth axis among all exits to alleviate gradient conflict while simultaneously promoting joint optimization for each exit. Subsequently, feature referencing enhances multi-scale features for distinct exits across varying depths to improve the model accuracy. Furthermore, DFS reduces the training operations with the reduced complexity of backpropagation. Experimental results on Cifar100 and ImageNet datasets exhibit that DFS provides up to a 50.00% reduction in training time and attains up to a 6.94% enhancement in accuracy when contrasted with baseline methods across diverse models and tasks. Budgeted batch classification evaluation on MSDNet demonstrates that DFS uses about 2× fewer average FLOPs per image to achieve the same classification accuracy as baseline methods on Cifar100. The code is available at https: //***/GongCheng1919/dfs. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

Securely Fine-tuning Pre-trained Encoders Against Adversaria...

引用

IEEE Symposium on Security and Privacy

作者： Ziqi Zhou Minghui Li Wei Liu Shengshan Hu Yechao Zhang Wei Wan Lulu Xue Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the *** this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six d

关键词： Training Adaptation models Sensitivity Accuracy Self-supervised learning Genetics Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural information Processing systems

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

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multipath Imaging for Vehicle Targets in Non-Los Urban SAR

Multipath Imaging for Vehicle Targets in Non-Los Urban SAR

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Yixin Wang Xiaolan Qiu Xuejiao Wen Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Beijing China Chinese Academy of Sciences Aerospace Information Research Institute Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China National Key Laboratory of Microwave Imaging Technology Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Laboratory of Spatial Information Intelligent Processing System Suzhou Aerospace Information Research Institute Suzhou China University of Science and Technology of China Hefei China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Integrating Synthetic Aperture Radar (SAR) imaging with unmanned aerial vehicles (UAVs) plays a crucial role in urban area surveillance and situational awareness, benefiting from the low cost, small size, and high flexibility of SAR carried by drones. However, the dense arrangement of high-rise buildings in urban environments creates Urban Canyons and numerous visual blind spots due to occlusion, which weakens the perception capability of SAR. Additionally, SAR imaging results of moving vehicles on the roads between buildings result in severe defocusing due to their non-cooperative motion. In this paper, we establish a vehicle signal model for SAR imaging with UAVs that considers the vehicle body’s translation and the wheels’ rotation. The range history modulation and imaging characteristics of returns caused by translation and micro-motion are derived. Simulation results validate the correctness of the theoretical analysis, and the proposed theory helps explain SAR imaging results, providing support for high-precision focusing and three-dimensional imaging of non-line-of-sight (NLOS) SAR images.

关键词： Visualization Surveillance Simulation Roads Urban areas Buildings Wheels

来源：评论

学校读者我要写书评

暂无评论

Neural Network and Collaborative Computing for Image-based Train Location Data Acquisition 5th

Neural Network and Collaborative Computing for Image-based...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Wu, Xiaoqing Song, Haifeng Wang, Peng Cheng, Jianfeng Zhou, Datian Dong, Hairong Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Beihang University School of Electronic and Information Engineering Beijing100191 China China Academy of Railway Sciences Group Co. Ltd. Beijing100044 China Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9789811939976

How to improve the performance and safety of the train has long been a question of great interest. The object of this study is to achieve the recognition of train speed and mileage that are provided by the train Driver Machine Interface (DMI) and reduce the time consumed by model training. For recognition part, a Convolutional Neural Network (CNN) and a Connectionist Temporal Classification (CTC) layer have been combined together to achieve an end-to-end recognition. For the part of time-consuming reduction, a collaborative computing was being utilized to offload the training tasks to each edge device. In addition, the process of offloading was modeled with Stochastic Petri Net (SPN). Overall, the recognition accuracy was significantly improved, compared to the traditional Optical Character Recognition (OCR) and CNNs, what is more, the time consumed on model training was also brought down as expect. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Symplectic Wigner Distribution in the Linear Canonical Transform Domain: Theory and Application

arXiv

引用

arXiv 2025年

作者： He, Yangfan Zhang, Zhichao School of Communication and Artificial Intelligence School of Integrated Circuits Nanjing Institute of Technology Nanjing211167 China School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing210044 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Computational Science Application of Hainan Province Hainan Normal University Haikou571158 China Key Laboratory of Numerical Simulation of Sichuan Provincial Universities School of Mathematics and Information Sciences Neijiang Normal University Neijiang641000 China

This paper devotes to combine the chirp basis function transformation and symplectic coordinates transformation to yield a novel Wigner distribution (WD) associated with the linear canonical transform (LCT), named as the symplectic WD in the LCT domain (SWDL). It incorporates the merits of the symplectic WD (SWD) and the WD in the LCT domain (WDL), achieving stronger capability in the linear frequency-modulated (LFM) signal frequency rate feature extraction while maintaining the same level of computational complexity. Some essential properties of the SWDL are derived, including marginal distributions, energy conservations, unique reconstruction, Moyal formula, complex conjugate symmetry, time reversal symmetry, scaling property, time translation property, frequency modulation property, and time translation and frequency modulation property. Heisenberg’s uncertainty principles of the SWDL are formulated, giving rise to three kinds of lower bounds attainable respectively by Gaussian enveloped complex exponential signal, Gaussian signal and Gaussian enveloped chirp signal. The optimal symplectic matrices corresponding to the highest time-frequency resolution are generated by solving the lower bound optimization (minimization) problem. The time-frequency resolution of the SWDL is compared with those of the SWD and WDL to demonstrate its superiority in LFM signals time-frequency energy concentration. A synthesis example is also carried out to verify the feasibility and reliability of the theoretical analysis. Copyright © 2025, The Authors. All rights reserved.

关键词： Wigner-Ville distribution

来源：评论

学校读者我要写书评

暂无评论

The impact of the atmospheric turbulence-development tendency on new particle formation: a common finding on three continents

引用

national Science Review 2021年第3期8卷 140-150页

作者： Hao Wu Zhanqing Li Hanqing Li Kun Luo Yuying Wang Peng Yan Fei Hu Fang Zhang Yele Sun Dongjie Shang Chunsheng Liang Dongmei Zhang Jing Wei Tong Wu Xiaoai Jin Xinxin Fan Maureen Cribb Marc L.Fischer Markku Kulmala Tuukka Pet?j? State Key Laboratory of Remote Sensing Science College of Global Change and Earth System ScienceBeijing Normal University ESSIC and Department of Atmospheric Science University of MarylandCollege Park State Key Laboratory of Clean Energy Utilization Zhejiang University School of Atmospheric Physics Nanjing University of Information Science and Technology Meteorological Observation Center China Meteorological Administration State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry Institute of Atmospheric Physics Chinese Academy of Sciences State Key Joint Laboratory of Environmental Simulation and Pollution Control College of Environmental Sciences and Engineering Peking University State Key Joint Laboratory of Environment Simulation and Pollution Control School of Environment Tsinghua University Lawrence Berkeley National Laboratory Institute for Atmospheric and Earth System Research/Physics Faculty of ScienceUniversity of Helsinki Aerosol and Haze Laboratory Beijing Advanced Innovation Center for Soft Matter Science and Engineering Beijing University of Chemical Technology Joint International Research Laboratory of Atmospheric and Earth System Sciences School of Atmospheric Sciences Nanjing University

A new mechanism of new particle formation(NPF) is investigated using comprehensive measurements of aerosol physicochemical quantities and meteorological variables made in three continents,including Beijing,China;the Southern Great Plains site in the USA;and SMEAR Ⅱ Station in Hyytiala,Finland.D espite the considerably different emissions of chemical species among the sites,a common relationship was found between the characteristics of NPF and the stability *** stability parameter(ζ=Z/L,where Z is the height above ground and L is the Monin-Obukhov length) is found to play an important role;it drops significantly before NPF as the atmosphere becomes more unstable,which may serve as an indicator of nucleation *** the atmosphere becomes unstable,the NPF duration is closely related to the tendency for turbulence development,which influences the evolution of the condensation ***,the unstable atmosphere may dilute pre-existing particles,effectively reducing the condensation sink,especially at coarse mode to foster *** new mechanism is confirmed by model simulations using a molecular dynamic model that mimics the impact of turbulence development on nucleation by inducing and intensifying homogeneous nucleation events.

关键词： new particle formation turbulence development molecular dynamic

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：