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

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

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

Sampling timing jitter in dispersion-managed frequency microcombs via a fiber interferometer

Sampling timing jitter in dispersion-managed frequency micro...

引用

CLEO: science and Innovations, S and I 2022

作者： Wang, Wenting Liu, Hao Melton, Tristan Yang, Jinghui Vinod, Abhinav Kumar Lim, Jinkang Jang, Yoon-Soo Zhou, Heng Yu, Mingbin Kwong, Dim-Lee DeVore, Peter Chou, Jason Wong, Chee Wei Fang Lu Mesoscopic Optics and Quantum Electronics Laboratory University of California Los AngelesCA90095 United States Key Lab of Optical Fiber Sensing and Communication Networks University of Electronic Science and Technology of China Chengdu611731 China Institute of Microelectronics A*STAR Singapore117865 Singapore State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information Technology Shanghai Industrial Technology Research Institute Shanghai China Lawrence Livermore National Laboratory LivermoreCA94550 United States

We characterized timing jitter of dispersion-managed frequency microcomb with femtosecond timing resolution through fiber interferometry for the first time. The measured timing jitter PSD and integrated timing jitter ... 详细信息

ISBN: (纸本)9781557528209

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Outage Probability and Power Allocation Analysis of AmBC-Enabled NOMA for Future IoT 23

Outage Probability and Power Allocation Analysis of AmBC-Ena...

引用

23rd IEEE International Conference on communication technology, ICCT 2023

作者： Wang, Chongye Liu, Yang Wang, Cheng-Xiang School of Internet of Things Engineering Jiangnan University Wuxi214122 China Nanjing University of Posts and Telecommunications Ministry of Education Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing210023 China School of Information Science and Engineering Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China

ISBN: (纸本)9798350325959

Ambient backscatter communication (AmBC) combined with non-orthogonal multiple access (NOMA) presents superior energy reusability and higher sum rate. However, existing studies failed to utilize the information of backscatter links. Therefore, to explore the impact of backscatter link, this paper employs three-user NOMA to improve the spectral efficiency. We propose a simple distance power allocation method to accomplish successive interference cancellation. Based on the Monte Carlo method, the outage probability of the proposal is analyzed. Our work provides a scheme for coexistence between AmBC and NOMA systems in the future Internet of Things. © 2023 IEEE.

关键词： Ambient backscatter communication non-orthogonal multiple access outage probability power allocation

来源：评论

学校读者我要写书评

暂无评论

Adaptive and Cooperative Resource Scheduling for Satellite-Terrestrial Networks

Adaptive and Cooperative Resource Scheduling for Satellite-T...

引用

GLOBECOM 2022 - 2022 IEEE Global communications Conference

作者： Yixin Wang Di Zhou Min Sheng Jiandong Li State Key Lab of ISN Information Science Institute Xidian University Xi'an Shaanxi China Science and Technology on Communication Networks Laboratory Shijiazhuang China

ISBN: (纸本)9781665435413

Satellite-terrestrial networks (STNs) consisting of satellite segment and ground segment have been regarded as a desirable solution for 6G. Efficient cooperative resource scheduling strategies, which cover the cooperation in satellite segment for data relay and the cooperation between satellite segment and ground segment for data downloading, play a pivotal role in enhancing the system performance in STNs. Since the dynamic channel condition and energy feeding greatly influence the network status, cooperative resource scheduling should be adaptive to the future environmental fluctuation. In this paper, we model the cooperative resource scheduling problem in STNs as a resource limited Markov Decision Process (MDP). Considering the fact that satellites are unaware of future environmental status, the traditional static optimization solution is infeasible. Therefore, we propose a Deep Reinforcement Learning (DRL) based Cooperative Store-and-Relay Resource Scheduling Algorithm (CSR-RSA), where inter-satellite links are utilized to coordinate with intermittent satellite-ground links for improving the transmission performance of the network. By exploiting the proposed CSR-RSA, the well-trained neural networks can be obtained to generate the adaptive and cooperative resource scheduling strategy without the knowledge of future environmental status. Simulation results verify the effectiveness of the proposed algorithm compared with traditional algorithms.

关键词： 6G mobile communication Adaptation models Satellites Adaptive systems Scheduling algorithms Heuristic algorithms Simulation

来源：评论

学校读者我要写书评

暂无评论

Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition

arXiv

引用

arXiv 2025年

作者： Xie, Yuankun Wang, Xiaopeng Wang, Zhiyong Fu, Ruibo Wen, Zhengqi Cao, Songjun Ma, Long Li, Chenxing Cheng, Haonnan Ye, Long State Key Laboratory of Media Convergence and Communication Communication University of China China School of Artificial Intelligence University of Chinese Academy of Sciences China Institute of Automation Chinese Academy of Sciences China Beijing National Research Center for Information Science and Technology Tsinghua University China YouTu Lab Tencent China AI Lab Tencent China

Current research in audio deepfake detection is gradually transitioning from binary classification to multi-class tasks, referred as audio deepfake source tracing task. However, existing studies on source tracing consider only closed-set scenarios and have not considered the challenges posed by open-set conditions. In this paper, we define the Neural Codec Source Tracing (NCST) task, which is capable of performing open-set neural codec classification and interpretable ALM detection. Specifically, we constructed the ST-Codecfake dataset for the NCST task, which includes bilingual audio samples generated by 11 state-of-the-art neural codec methods and ALM-based out-of-distribution (OOD) test samples. Furthermore, we establish a comprehensive source tracing benchmark to assess NCST models in open-set conditions. The experimental results reveal that although the NCST models perform well in in-distribution (ID) classification and OOD detection, they lack robustness in classifying unseen real audio. The ST-codecfake dataset1 and code2 are available. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Byzantine-resilient Federated Learning With Adaptivity to Data Heterogeneity

arXiv

引用

arXiv 2024年

作者： Zuo, Shiyuan Yan, Xingrun Fan, Rongfei Hu, Han Shan, Hangguan Quek, Tony Q.S. The School of Cyberspace Science and Technology Beijing Institute of Technology Beijing100081 China The School of Information and Electronics Beijing Institute of Technology Beijing100081 China The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Hangzhou China The Singapore University of Technology and Design Singapore487372 Singapore The Yonsei Frontier Lab Yonsei University Korea Republic of

This paper deals with federated learning (FL) in the presence of malicious Byzantine attacks and data heterogeneity. A novel Robust Average Gradient Algorithm (RAGA) is proposed, which leverages the geometric median for aggregation and can freely select the round number for local updating. Different from most existing resilient approaches, which perform convergence analysis based on strongly-convex loss function or homogeneously distributed dataset, we conduct convergence analysis for not only strongly-convex but also non-convex loss function over heterogeneous dataset. According to our theoretical analysis, as long as the fraction of dataset from malicious users is less than half, RAGA can achieve convergence at rate O(1/T2/3−δ) where T is the iteration number and δ ∈ (0, 2/3) for non-convex loss function, and at linear rate for strongly-convex loss function. Moreover, stationary point or global optimal solution is proved to obtainable as data heterogeneity vanishes. Experimental results corroborate the robustness of RAGA to Byzantine attacks and verifies the advantage of RAGA over baselines on convergence performance under various intensity of Byzantine attacks, for heterogeneous dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

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

Dispersion-Suppressed Mode Depletion by Exceptional Points for On-Chip Nonlinear Optics

引用

Physical Review Applied 2022年第3期18卷 034028-034028页

作者： Boqing Zhang Nuo Chen Haofan Yang Yuntian Chen Jianji Dong Heng Zhou Xinliang Zhang Jing Xu School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan 430074 China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan 430074 China Key Lab of Optical Fiber Sensing and Communication Networks University of Electronic Science and Technology of China Chengdu 611731 China

Dispersion-suppressed mode depletion in a resonant cavity is usually challenging due to the entanglement of amplitude and phase response dictated by the Kramers-Kronig relationship. In this study, we examine the dispersion-suppressed mode depletion induced by parity–time- (PT-) symmetric dual resonators by taking advantage of the exotic property at the exceptional point (EP). We show that this technique can modify the linear spectrum of an optical resonator for relaxed phase-matching conditions in nonlinear optics, thus profoundly altering the nonlinear behavior of integrated Kerr combs. Indeed, dissipation-induced modulation instability (MI) is predicted and numerically verified in normal group-velocity dispersion (GVD) microresonators, and the single-soliton-generation probability is greatly enhanced in the anomalous GVD regime. The merging of two vibrant disciplines, i.e., non-Hermitian optics and nonlinear optics, especially Kerr microcombs, can deepen our understanding of non-Hermitian optical frequency combs and opens broad applications ranging from fiber-optic communications, microwave photonics, and ultrafast optics to quantum state manipulations.

关键词： Integrated optics Nonlinear optics Optical solitons Non-Hermitean systems Optical microcavities PT-symmetry Kerr effect Whispering gallery mode resonators

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：