检索结果-南通市图书馆

Mitigate noisy data for smart IoT via GAN based machine unlearning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第3期67卷 62-78页

作者： Zhuo MA Yilong YANG Yang LIU Xinjing LIU Jianfeng MA School of Cyber Engineering Xidian University State Key laboratory of Integrated services Networks (ISN)

With the development of IoT applications, machine learning dramatically improves the utility of variable IoT systems such as autonomous driving. Although the pretrain-finetune framework can cope well with data heterogeneity in complex IoT scenarios, the data collected by sensors often contain unexpected noisy data, e.g., out-of-distribution(OOD) data, which leads to the reduced performance of fine-tuned models. To resolve the problem, this paper proposes Mu GAN, a method that can mitigate the side-effect of OOD data via the generative adversarial network(GAN)-based machine unlearning. Mu GAN follows a straightforward but effective idea to mitigate the performance loss caused by OOD data, i.e., “flashbacking” the model to the condition where OOD data are excluded from model training. To achieve the goal, we design an adversarial game, where a discriminator is trained to identify whether a sample belongs to the training set by observing the confidence score. Meanwhile, a generator(i.e., the target model) is updated to fool the discriminator into believing that the OOD data are not included in the training set but others do. The experimental results show that benefiting from the high unlearning rate(more than 90%) and retention rate(99%), Mu GAN succeeds in lowering the model performance degradation caused by OOD data from 5.88% to 0.8%.

关键词： machine unlearning generative adversarial network out of distribution data Internet of Thing neural network

Cognitive Jammers Assisted Covert Communication in Cognitive Radio Networks

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第9期21卷 75-89页

作者： Liu Changjun Shi Jia Tie Zhuangzhuang Wang Yongchao The State Key laboratory of Integrated services Networks Xidian UniversityXi’an 710071China

In this work,we investigate the covert communication in cognitive radio(CR)networks with the existence of multiple cognitive jammers(CJs).Specifically,the secondary transmitter(ST)helps the primary transmitter(PT)to relay information to primary receiver(PR),as a reward,the ST can use PT's spectrum to transmit private information against the eavesdropper(Eve)under the help of one selected cognitive jammer(CJ).Meanwhile,we propose three jammer-selection schemes,namely,link-oriented jammer selection(LJS),min-max jammer selection(MMJS)and random jammer selection(RJS).For each scheme,we analyze the average covert throughput(ACT)and covert outage probability(COP).Our simulation results show that CJ is helpful to ST's covert communication,the expected minimum detection error probability and ACT can be significantly improved with the increase of false alarm of ***,the LJS scheme achieves best performance in ACT and COP,followed by RJS scheme,and MMJS scheme shows the worst performance.

关键词： cognitive jammer cognitive radio covert communication performance analysis

维普期刊数据库

A Distributed Self-Tallying Electronic Voting System Using the Smart Contract

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第4期33卷 1063-1076页

作者： Jingyu YAO Bo YANG Tao WANG Wenzheng ZHANG School of Computer Science Shaanxi Normal University State Key laboratory of Integrated services Networks Xidian University Science and Technology on Communication Security laboratory

For electronic voting(e-voting) with a trusted authority, the ballots may be discarded or tampered, so it is attractive to eliminate the dependence on the trusted party. An e-voting protocol, where the final voting result can be calculated by any entity, is known as self-tallying e-voting protocol. To the best of our knowledge, addressing both abortive issue and adaptive issue simultaneously is still an open problem in self-tallying e-voting *** Ethereum blockchain with cryptographic technologies, we present a decentralized self-tallying e-voting protocol. We solve the above problem efficiently by utilizing optimized Group Encryption Scheme and standard Exponential El Gamal Cryptosystem. We use zero-knowledge proof and homomorphic encryption to protect votes' secrecy and achieve self-tallying. All ballots can be verified by anyone and the final voting result can be calculated by any entity. In addition, using the paradigm of score voting and “1-out-of-k” proof, our e-voting system is suitable for a wide range of application scenarios. Experiments show that our protocol is more competitive and more suitable for large-scale voting.

关键词： Electronic voting systems Smart contracts Blockchains Cryptocurrency Electronic voting Homomorphic encryption Standards

Resource Allocation in Multi-User Cellular Networks:A Transformer-Based Deep Reinforcement Learning Approach

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第5期21卷 77-96页

作者： Zhao Di Zheng Zhong Qin Pengfei Qin Hao Song Bin State Key laboratory of Integrated services Networks Xidian University710071China China Academy of Space Technology Beijing 100081China

To meet the communication services with diverse requirements,dynamic resource allocation has shown increasing *** this paper,we consider the multi-slot and multi-user resource allocation(MSMU-RA)in a downlink cellular scenario with the aim of maximizing system spectral efficiency while guaranteeing user *** first model the MSMURA problem as a dual-sequence decision-making process,and then solve it by a novel Transformerbased deep reinforcement learning(TDRL)***,the proposed TDRL approach can be achieved based on two aspects:1)To adapt to the dynamic wireless environment,the proximal policy optimization(PPO)algorithm is used to optimize the multi-slot RA strategy.2)To avoid co-channel interference,the Transformer-based PPO algorithm is presented to obtain the optimal multi-user RA scheme by exploring the mapping between user sequence and resource *** results show that:i)the proposed approach outperforms both the traditional and DRL methods in spectral efficiency and user fairness,ii)the proposed algorithm is superior to DRL approaches in terms of convergence speed and generalization performance.

关键词： dynamic resource allocation multi-user cellular network spectrum efficiency user fairness

维普期刊数据库

A Recursive DRL-Based Resource Allocation Method for Multibeam Satellite Communication Systems

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第5期33卷 1286-1295页

作者： Haowei MENG Ning XIN Hao QIN Di ZHAO State Key laboratory of Integrated services Networks Xidian University China Academy of Space Technology Institute of Telecommunication Satellite

Optimization-based radio resource management(RRM) has shown significant performance gains on high-throughput satellites(HTSs). However, as the number of allocable on-board resources increases, traditional RRM is difficult to apply in real satellite systems due to its intense computational complexity. Deep reinforcement learning(DRL) is a promising solution for the resource allocation problem due to its model-free advantages. Nevertheless, the action space faced by DRL increases exponentially with the increase of communication scale, which leads to an excessive exploration cost of the algorithm. In this paper, we propose a recursive frequency resource allocation algorithm based on long-short term memory(LSTM) and proximal policy optimization(PPO), called PPO-RA-LOOP,where RA means resource allocation and LOOP means the algorithm outputs actions in a recursive manner. Specifically, the PPO algorithm uses LSTM network to recursively generate sub-actions about frequency resource allocation for each beam, which significantly cuts down the action space. In addition, the LSTM-based recursive architecture allows PPO to better allocate the next frequency resource by using the generated sub-actions information as a prior knowledge, which reduces the complexity of the neural network. The simulation results show that PPO-RA-LOOP achieved higher spectral efficiency and system satisfaction compared with other frequency allocation algorithms.

关键词： High-throughput satellites Proximal policy optimization Deep reinforcement learning Long-short term memory High-throughput satellites Proximal policy optimization Deep reinforcement learning Long-short term memory OPTIMIZATION POWER

Blind Recognition of Non-Binary LDPC Codes Based on Ant Colony Optimization

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第10期 59-69页

作者： Guan Mengsheng Gao Wanting Chen Qi Zhu Min Bai Baoming State Key laboratory of Integrated services Networks Xidian University

This paper introduces a novel blind recognition of non-binary low-density parity-check(LDPC)codes without a candidate set, using ant colony optimization(ACO) algorithm over additive white Gaussian noise(AWGN) channels. Specifically, the scheme that effectively combines the ACO algorithm and the non-binary elements over finite fields is ***, an improved, simplified elitist ACO algorithm based on soft decision reliability is introduced to recognize the parity-check matrix over noisy channels. Simulation results show that the recognition rate continuously increases with an increased signalto-noise ratio(SNR) over the AWGN channel.

关键词：

Optimal regulation of flexible loads in rural residential buildings considering mobile batteries:A case study in Shaanxi Province

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Building Simulation 2024年第7期17卷 1065-1083页

作者： Xi Luo WenceShi School of Building services Science and Engineering Xian University of Architecture and Technology(XAUAT)Xi'an 710055China State Key laboratory of Green Building Xi'an 710055China

While the grid-connected capacity of rural household photovoltaics is increasing rapidly,achieving dynamic supply-demand matching despite fluctuations in solar energy is *** the rapid development of rural electrification,battery-powered technologies,such as electric vehicles and electric agricultural machinery,are becoming increasingly popular in rural *** this context,utilizing idle mobile batteries to assist in energy storage for rural residential buildings offers a new way to solve the problem of dynamic supply-demand *** this study,a field survey was conducted on several typical fruit-growing villages in the Central Shaanxi Plain in Shaanxi Province of *** rural households were selected to calculate the electricity loads of the residential buildings,with due consideration to the intervention of mobile *** the premise of installing 3 kW household photovoltaic systems in rural households,an economical efficiency-oriented model was built for the optimal regulation of flexible *** results were compared in the context of two patterns of electricity consumption,i.e.,unidirectional charging of mobile batteries from buildings and bidirectional charging and discharging between mobile batteries and *** bidirectional pattern significantly increased the photovoltaic consumption of typical rural households on various typical ***,during both scenarios of not implementing time-of-use and implementing time-of-use,the typical day of the winter slack farming season exhibited the best photovoltaic consumption effect among all types of typical ***,the bidirectional pattern also result in a significant increase in the annual electricity sales revenues for typical rural households.

关键词： demand-side response flexible load mobile battery household photovoltaics

Energy consumption simulations of rural residential buildings considering differences in energy use behavior among family members

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Building Simulation 2024年第8期17卷 1335-1358页

作者： Xi Luo Lina Du School of Building services Science and Engineering Xi'an University of Architecture and Technology(XAUAT)Xi'an 710055China State Key laboratory of Green Building Xi'an 710055China

The“average occupant”methodology is widely used in energy consumption simulations of residential buildings;however,it fails to consider the differences in energy use behavior among family *** on a field survey on the Central Shaanxi Plain,to identify the energy use behavior patterns of typical families,a stochastic energy use behavior model considering differences in energy use behavior among family members was proposed,to improve the accuracy of energy consumption simulations of residential *** results indicated that the surveyed rural families could be classified into the following four types depending on specific energy use behavior patterns:families of one elderly couple,families of one middle-aged couple,families of one elderly couple and one child,and families of one couple and one ***,on typical summer days,the results of daily building energy consumption simulation obtained by the“average occupant”methodology were 25.39%and 28%lower than the simulation results obtained by the model proposed in this study for families of one elderly couple and families of one middle-aged couple,and 13.05%and 23.05%higher for families of one elderly couple and one child,and families of one couple and one *** typical winter days,for the four types of families,the results of daily building energy consumption simulation obtained by the“average occupant”methodology were 21.69%,10.84%,1.21%,and 8.39%lower than the simulation results obtained by the model proposed in this study,respectively.

关键词： typical energy use behavior pattern differences in occupant behavior building energy consumption simulation stochastic energy use behavior simulation

An Active Deception Defense Model Based on Address Mutation and Fingerprint Camouflage

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第7期21卷 212-223页

作者： Wang Shuo Chu Jiang Pei Qingqi Shao Feng Yuan Shuai Zhong Xiaoge State Key laboratory of Astronautic Dynamics Xi’an Satellite Control CenterXi’an 710043China State Key laboratory of Integrated services Networks Xidian UniversityXi’an 710071China Shaanxi Key laboratory of Blockchain and Secure Computing Xidian UniversityXi’an 710071China

The static and predictable characteristics of cyber systems give attackers an asymmetric advantage in gathering useful information and launching *** reverse this asymmetric advantage,a new defense idea,called Moving Target Defense(MTD),has been proposed to provide additional selectable measures to complement traditional ***,MTD is unable to defeat the sophisticated attacker with fingerprint tracking *** overcome this limitation,we go one step beyond and show that the combination of MTD and Deception-based Cyber Defense(DCD)can achieve higher performance than either of *** particular,we first introduce and formalize a novel attacker model named Scan and Foothold Attack(SFA)based on cyber kill ***,we develop probabilistic models for SFA defenses to provide a deeper analysis of the theoretical effect under different defense *** models quantify attack success probability and the probability that the attacker will be deceived under various conditions,such as the size of address space,and the number of hosts,attack analysis ***,the experimental results show that the actual defense effect of each strategy almost perfectly follows its probabilistic ***,the defense strategy of combining address mutation and fingerprint camouflage can achieve a better defense effect than the single address mutation.

关键词： address mutation deception defense fingerprint camouflage moving target defense probabilistic model

维普期刊数据库