检索结果-内蒙古大学图书馆

Deep Learning-Based Decoding of Block Markov Superposition Transmission

学校读者我要写书评

暂无评论

Deep Learning-Based Decoding of Block Markov Superposition T...

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Sheng Bi Qianfan Wang Zengzhe Chen Jiachen Sun Xiao Ma School of Data and Computer Science Sun Yat-sen University Guangzhou China School of Electronics and Communication Engineering Sun Yat-sen University Guangzhou China School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

In this paper, we present deep learning-based decoding of block Markov superposition transmission (BMST). For the basic code, a deep neural network (DNN) is trained, providing with good decoding performance. The complexity of the trained DNN can be reduced by removing those negligibly small coefficients. For the BMST code, we introduce a sliding window decoding algorithm, which integrates the DNN decoder of the basic code in an iterative manner. Numerical results show that the performance of our proposed scheme is close to that of the BMST system with conventional decoders and matches well with the corresponding lower bound of BMST. The above results verify that the extra gain and lower bound of BMST are effective for neural network decoder and thus demonstrate the universality of BMST.

关键词： Decoding Machine learning Encoding Iterative decoding Microsoft Windows Neural networks Markov processes

MISA: UNVEILING THE VULNERABILITIES IN SPLIT FEDERATED LEARNING

学校读者我要写书评

暂无评论

arXiv 2023年

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

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 robustness. In this paper, we present a novel poisoning attack known as 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 availab.lity of SFL, underscoring the imperative for academia and industry to accord this matter due attention. Copyright © 2023, The Authors. All rights reserved.

关键词：

Joint Participation Incentive and Network Pricing Design for Federated Learning 42

学校读者我要写书评

暂无评论

Joint Participation Incentive and Network Pricing Design for...

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Ding, Ningning Gao, Lin Huang, Jianwei Northwestern University Department of Electrical and Computer Engineering EvanstonIL60208 United States Shenzhen Research Institute of Big Data Shenzhen518172 China Harbin Institute of Technology Sch. of Electronics and Info. Eng. and the Guangdong Prov. Key Lab. of Aerosp. Commun. and Networking Technol. Shenzhen China The Chinese University of Hong Kong Shenzhen School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen518172 China

ISBN: (纸本)9798350334142

Federated learning protects users' data privacy though sharing users' local model parameters (instead of raw data) with a server. However, when massive users train a large machine learning model through federated learning, the dynamically varying and often heavy communication overhead can put significant pressure on the network operator. The operator may choose to dynamically change the network prices in response, which will eventually affect the payoffs of the server and users. This paper considers the under-explored yet important issue of the joint design of participation incentives (for encouraging users' contribution to federated learning) and network pricing (for managing network resources). Due to heterogeneous users' private information and multi-dimensional decisions, the optimization problems in Stage I of multi-stage games are non-convex. Nevertheless, we are able to analytically derive the corresponding optimal contract and pricing mechanism through proper transformations of constraints, variables, and functions, under both vertical and horizontal interaction structures of the participants. We show that the vertical structure is better than the horizontal one, as it avoids the interests misalignment between the server and the network operator. Numerical results based on real-world datasets show that our proposed mechanisms decrease server's cost by up to 24.87% comparing with the state-of-the-art benchmarks. © 2023 IEEE.

关键词： Costs

ECLIPSE: Expunging Clean-lab.l Indiscriminate Poisons via Sparse Diffusion Purification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei 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 China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-lab.l indiscriminate poisoning attacks add invisible perturbations to correctly lab.led training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is availab.e at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

Deep Generative Network for Image Inpainting with Gradient Semantics and Spatial-Smooth Attention

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Sheng, Ziqi Xu, Wenbo Lin, Cong Lu, Wei School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China Applied Laboratory of Dig Data and Education Statistics School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou510006 China

As a powerful means of tampering in image content security area, image inpainting based on deep generative networks can yield visually appealing outputs but often produces ambiguous artifacts, particularly in boundary and high semantic areas. To address this issue, a novel end-to-end network with gradient semantics and spatial-smooth attention (GS-SSA) is proposed, which combines a gradient learning network and an image inpainting network. The gradient learning network is meant to properly anticipate the gradient semantics in the hole region and get a complete gradient semantic map. The image inpainting network utilizes the complete gradient semantic map to better repair the missing pixels and obtain the final inpainting results. Moreover, spatial-smooth attention is introduced into the image inpainting network, considering the spatial structural relations and the surrounding information in the hole region respectively. © 2023, The Authors. All rights reserved.

关键词： Semantics

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

学校读者我要写书评

暂无评论

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yanzuo Lu Manlin Zhang Andy J Ma Xiaohua Xie Jianhuang Lai School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pazhou Lab (HuangPu) Guangzhou China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Diffusion model is a promising approach to image generation and has been employed for Pose-Guided Person Image Synthesis (PGPIS) with competitive performance. While existing methods simply align the person appearance to the target pose, they are prone to overfitting due to the lack of a high-level semantic understanding on the source person image. In this paper, we propose a novel Coarse-to-Fine Latent Diffusion (CFLD) method for PGPIS. In the absence of image-caption pairs and textual prompts, we de-velop a novel training paradigm purely based on images to control the generation process of a pre-trained text-to-image diffusion model. A perception-refined decoder is designed to progressively refine a set of learnable queries and extract semantic understanding of person images as a coarse-grained prompt. This allows for the decoupling of fine-grained appearance and pose information controls at different stages, and thus circumventing the potential over-fitting problem. To generate more realistic texture details, a hybrid- granularity attention module is proposed to encode multi-scale fine-grained appearance features as bias terms to augment the coarse-grained prompt. Both quantitative and qualitative experimental results on the DeepFashion benchmark demonstrate the superiority of our method over the state of the arts for PGPIS. Code is availab.e at https://***/YanzuoLu/CFLD.

关键词： Training Image synthesis Semantics Text to image Process control Diffusion models Generators

DRL-M4MR: An Intelligent Multicast Routing Approach Based on DQN Deep Reinforcement Learning in SDN

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Chenwei Ye, Miao Xue, Xingsi Lv, Jianhui Jiang, Qiuxiang Wang, Yong School of Information and Communication Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin University of Electronic Technology Guilin541004 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China Peng Cheng Lab. Guangdong Shenzhen518038 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

Traditional multicast routing methods have some problems in constructing a multicast tree, such as limited access to network state information, poor adaptability to dynamic and complex changes in the network, and inflexible data forwarding. To address these defects, the optimal multicast routing problem in software-defined networking (SDN) is tailored as a multi-objective optimization problem, and an intelligent multicast routing algorithm DRL-M4MR based on the deep Q network (DQN) deep reinforcement learning (DRL) method is designed to construct a multicast tree in SDN. First, the multicast tree state matrix, link bandwidth matrix, link delay matrix, and link packet loss rate matrix are designed as the state space of the DRL agent by combining the global view and control of the SDN. Second, the action space of the agent is all the links in the network, and the action selection strategy is designed to add the links to the current multicast tree under four cases. Third, single-step and final reward function forms are designed to guide the intelligence to make decisions to construct the optimal multicast tree. The experimental results show that, compared with existing algorithms, the multicast tree construct by DRL-M4MR can obtain better bandwidth, delay, and packet loss rate performance after training, and it can make more intelligent multicast routing decisions in a dynamic network environment. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

Unsupervised person re-identification by deep asymmetric metric embedding

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yu, Hong-Xing Wu, Ancong Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University Guangzhou510275 China Guangdong Province Key Laboratory of Information Security China School of Electronics and Information Technology Sun Yat-sen University Guangzhou510275 China Collaborative Innovation Center of High Performance Computing NUDT China School of Data and Computer Science Sun Yat-sen University Guangzhou510275 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Person re-identification (Re-ID) aims to match identities across non-overlapping camera views. Researchers have proposed many supervised Re-ID models which require quantities of cross-view pairwise lab.lled data. This limits their scalab.lities to many applications where a large amount of data from multiple disjoint camera views is availab.e but unlab.lled. Although some unsupervised Re-ID models have been proposed to address the scalab.lity problem, they often suffer from the view-specific bias problem which is caused by dramatic variances across different camera views, e.g., different illumination, viewpoints and occlusion. The dramatic variances induce specific feature distortions in different camera views, which can be very disturbing in finding cross-view discriminative information for Re-ID in the unsupervised scenarios, since no lab.l information is availab.e to help alleviate the bias. We propose to explicitly address this problem by learning an unsupervised asymmetric distance metric based on cross-view clustering. The asymmetric distance metric allows specific feature transformations for each camera view to tackle the specific feature distortions. We then design a novel unsupervised loss function to embed the asymmetric metric into a deep neural network, and therefore develop a novel unsupervised deep framework named the DEep Clustering-based Asymmetric MEtric Learning (DECAMEL). In such a way, DECAMEL jointly learns the feature representation and the unsupervised asymmetric metric. DECAMEL learns a compact cross-view cluster structure of Re-ID data, and thus help alleviate the view-specific bias and facilitate mining the potential cross-view discriminative information for unsupervised Re-ID. Extensive experiments on seven benchmark datasets whose sizes span several orders show the effectiveness of our framework. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

ZSTAD: Zero-shot temporal activity detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Lingling Chang, Xiaojun Liu, Jun Luo, Minnan Wang, Sen Ge, Zongyuan Hauptmann, Alexander School of Computer Science and Technology Xian Jiaotong University Xian China Ministry of Education Key Lab For Intelligent Networks and Network Security Xian China Faculty of Information Technology Monash University Australia National Engineering Lab for Big Data Analytics Xian Jiaotong University Xian China School of Information Technology and Electrical Engineering University of Queensland Australia School of Computer Science Carnegie Mellon University United States

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailab.e videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity lab.ls and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning