检索结果-南通市图书馆

DLP:towards active defense against backdoor attacks with decoupled learning process

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Cybersecurity 2024年第1期7卷 122-134页

作者： Zonghao Ying Bin Wu State Key Laboratory of information security Institute of Information EngineeringChinese Academy of SciencesBeijingChina School of Cyber security University of Chinese Academy of SciencesBeijingChina

Deep learning models are well known to be susceptible to backdoor attack,where the attacker only needs to provide a tampered dataset on which the triggers are injected.Models trained on the dataset will passively implant the backdoor,and triggers on the input can mislead the models during testing.Our study shows that the model shows different learning behaviors in clean and poisoned subsets during training.Based on this observation,we propose a general training pipeline to defend against backdoor attacks actively.Benign models can be trained from the unreli-able dataset by decoupling the learning process into three stages,i.e.,supervised learning,active unlearning,and active semi-supervised fine-tuning.The effectiveness of our approach has been shown in numerous experiments across various backdoor attacks and datasets.

关键词： Deep learning Backdoor attack Active defense

TransTM:A device-free method based on time-streaming multiscale transformer for human activity recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第2期32卷 619-628页

作者： Yi Liu Weiqing Huang Shang Jiang Bobai Zhao Shuai Wang Siye Wang Yanfang Zhang institute of information Engineering Chinese Academy of Sciences School of Cyber SecurityUniversity of Chinese Academy of SciencesBeijingChina School of information Management Beijing Information Science and Technology UniversityBeijingChina

RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.

关键词： Human activity recognition RFID Transformer

维普期刊数据库

security estimation of LWE via BKW algorithms

在线全文

学校读者我要写书评

暂无评论

Cybersecurity 2024年第1期7卷 71-87页

作者： Yu Wei Lei Bi Xianhui Lu Kunpeng Wang SKLOIS Institute of Information EngineeringCASBeijingChina School of Cyber security University of Chinese Academy of SciencesBeijingChina

The Learning With Errors(LWE)problem is widely used in lattice-based cryptography,which is the most promising post-quantum cryptography direction.There are a variety of LWE-solving methods,which can be classified into four groups:lattice methods,algebraic methods,combinatorial methods,and exhaustive searching.The Blum–Kalai–Wasserman(BKW)algorithm is an important variety of combinatorial algorithms,which was first presented for solving the Learning Parity With Noise(LPN)problem and then extended to solve LWE.In this paper,we give an overview of BKW algorithms for solving LWE.We introduce the framework and key techniques of BKW algorithms and make comparisons between different BKW algorithms and also with lattice methods by estimating concrete security of specific LWE instances.We also briefly discuss the current problems and potential future directions of BKW algorithms.

关键词： Post-quantum cryptography Learning with errors problem Lattice-based cryptography security estimation

Lightweight Res-Connection Multi-Branch Network for Highly Accurate Crowd Counting and Localization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2105-2122页

作者： Mingze Li Diwen Zheng Shuhua Lu College of information and Cyber security People’s Public Security University of ChinaBeijing102600China

Crowd counting is a promising hotspot of computer vision involving crowd intelligence analysis,achieving tremendous success recently with the development of deep learning.However,there have been stillmany challenges including crowd multi-scale variations and high network complexity,etc.To tackle these issues,a lightweight Resconnection multi-branch network(LRMBNet)for highly accurate crowd counting and localization is proposed.Specifically,using improved ShuffleNet V2 as the backbone,a lightweight shallow extractor has been designed by employing the channel compression mechanism to reduce enormously the number of network parameters.A light multi-branch structure with different expansion rate convolutions is demonstrated to extract multi-scale features and enlarged receptive fields,where the information transmission and fusion of diverse scale features is enhanced via residual concatenation.In addition,a compound loss function is introduced for training themethod to improve global context information correlation.The proposed method is evaluated on the SHHA,SHHB,UCF-QNRF and UCF_CC_50 public datasets.The accuracy is better than those of many advanced approaches,while the number of parameters is smaller.The experimental results show that the proposed method achieves a good tradeoff between the complexity and accuracy of crowd counting,indicating a lightweight and high-precision method for crowd counting.

关键词： Crowd counting Res-connection multi-branch compound loss function

Modulated symbol-based one-time pad secure transmission scheme using physical layer keys

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第1期67卷 221-239页

作者： Xiaoyan HU Zheng WAN Kaizhi HUANG Liang JIN Mengyao YAN Yajun CHEN Jinmei YANG information Engineering University Purple Mountain Laboratories for Network and Communication security

This paper proposes a novel modulated symbols-based one-time pad(SOTP) secure transmission scheme using physical layer keys.Unlike classical physical layer key generation and exclusive OR(XOR)encryption in the discrete binary space,we design a framework for modulated symbols-based one-time pad(OTP) encryption,where the cryptographic primitive and mathematical model of SOTP is given to build a practical cryptographic protocol.Compared with existing physical layer encryption(PLE) schemes,we provide rigorous proof that the framework can meet perfect secrecy and correctness requirements.In addition,we provide a specific scheme of physical layer OTP secure transmission for quadrature amplitude modulation(QAM) and phase-shift keying(PSK) symbols based on physical layer keys.This scheme realizes the unification of bit encryption and symbol encryption,which can adaptively select the quantization level according to the signal-to-noise ratio(SNR) to minimize the symbol error rate(SER).Further,we analyze the performance quantitatively and derive the closed-form expressions of SER,which indicates that the proposed scheme has a lower SER.Finally,simulation results verify that the proposed symbol-wise OTP secure transmission scheme can achieve perfect secrecy and high reliability.

关键词： physical layer security one-time pad wireless channel physical layer encryption perfect secrecy

Heterophilic Graph Neural Network Based on Spatial and Frequency Domain Adaptive Embedding Mechanism

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第5期139卷 1701-1731页

作者： Lanze Zhang Yijun Gu Jingjie Peng College of information and Cyber security People’s Public Security University of ChinaBeijing100038China

Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggregation and embedding.However,in heterophilic graphs,nodes from different categories often establish connections,while nodes of the same category are located further apart in the graph topology.This characteristic poses challenges to traditional GNNs,leading to issues of“distant node modeling deficiency”and“failure of the homophily assumption”.In response,this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks(SFA-HGNN),which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned issues.Specifically,for the first problem,we propose the“Distant Spatial Embedding Module”,aiming to select and aggregate distant nodes through high-order randomwalk transition probabilities to enhance modeling capabilities.For the second issue,we design the“Proximal Frequency Domain Embedding Module”,constructing adaptive filters to separate high and low-frequency signals of nodes,and introduce frequency-domain guided attention mechanisms to fuse the relevant information,thereby reducing the noise introduced by the failure of the homophily assumption.We deploy the SFA-HGNN on six publicly available heterophilic networks,achieving state-of-the-art results in four of them.Furthermore,we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation,demonstrating a positive correlation between“node structural similarity”,“node attribute vector similarity”,and“node homophily”in heterophilic networks.

关键词： Heterophilic graph graph neural network graph representation learning failure of the homophily assumption

Attention-Enhanced Voice Portrait Model Using Generative Adversarial Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 837-855页

作者： Jingyi Mao Yuchen Zhou YifanWang Junyu Li Ziqing Liu Fanliang Bu School of information Network security People’s Public Security University of ChinaBeijing100038China

Voice portrait technology has explored and established the relationship between speakers’ voices and their facialfeatures, aiming to generate corresponding facial characteristics by providing the voice of an unknown speaker.Due to its powerful advantages in image generation, Generative Adversarial Networks (GANs) have now beenwidely applied across various fields. The existing Voice2Face methods for voice portraits are primarily based onGANs trained on voice-face paired datasets. However, voice portrait models solely constructed on GANs facelimitations in image generation quality and struggle to maintain facial similarity. Additionally, the training processis relatively unstable, thereby affecting the overall generative performance of the model. To overcome the abovechallenges,wepropose a novel deepGenerativeAdversarialNetworkmodel for audio-visual synthesis, namedAVPGAN(Attention-enhanced Voice Portrait Model using Generative Adversarial Network). This model is based ona convolutional attention mechanism and is capable of generating corresponding facial images from the voice ofan unknown speaker. Firstly, to address the issue of training instability, we integrate convolutional neural networkswith deep GANs. In the network architecture, we apply spectral normalization to constrain the variation of thediscriminator, preventing issues such as mode collapse. Secondly, to enhance the model’s ability to extract relevantfeatures between the two modalities, we propose a voice portrait model based on convolutional attention. Thismodel learns the mapping relationship between voice and facial features in a common space from both channeland spatial dimensions independently. Thirdly, to enhance the quality of generated faces, we have incorporated adegradation removal module and utilized pretrained facial GANs as facial priors to repair and enhance the clarityof the generated facial images. Experimental results demonstrate that our AVP-GAN achieved a cosine similarity of0.511, outperforming the performance of our comparison mo

关键词： Cross-modal generation GANs voice portrait technology face synthesis

Robust adaptive radar beamforming based on iterative training sample selection using kurtosis of generalized inner product statistics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2024年第1期35卷 24-30页

作者： TIAN Jing ZHANG Wei School of information and Electronics Beijing Institute of TechnologyBeijing 100081China National Key Laboratory of Electromagnetic Space security Chengdu 610036China

In engineering application,there is only one adaptive weights estimated by most of traditional early warning radars for adaptive interference suppression in a pulse reputation interval(PRI).Therefore,if the training samples used to calculate the weight vector does not contain the jamming,then the jamming cannot be removed by adaptive spatial filtering.If the weight vector is constantly updated in the range dimension,the training data may contain target echo signals,resulting in signal cancellation effect.To cope with the situation that the training samples are contaminated by target signal,an iterative training sample selection method based on non-homogeneous detector(NHD)is proposed in this paper for updating the weight vector in entire range dimension.The principle is presented,and the validity is proven by simulation results.

关键词： adaptive radar beamforming training sample selection non-homogeneous detector electronic jamming jamming suppression

维普期刊数据库

A Generalized MSST Algorithm for Counting Points of Elliptic Curves over■

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第4期37卷 1738-1754页

作者： LI Xiao LV Chang PAN Zhizhong Key Laboratory of Cyberspace security Defense Institute of Information Engineering Chinese Academy of Sciences School of Cyber security University of Chinese Academy of Sciences Huawei Technologies Co. Ltd.

Elliptic curve cryptography is an important part of nowaday's public key cryptosystem.Counting points of elliptic curves over finite fields is of great significance to the selection of safety curves.At present, there are many p-adic algorithms, such as SST algorithm, generalized AGM algorithm,Kedlaya algorithm, etc., which can deal with the situation of finite fields of small characteristics. In this paper, the authors generalize the MSST algorithm of characteristic 2 to general fields of odd characteristic, and propose the generalized MSST algorithm. The generalized MSST algorithm is achieved by combining the advantages of the SST algorithm and the generalized AGM algorithm. If the time complexity of the multiplication of two n-bit numbers is denoted as O（nμ）, then the time complexity of the generalized MSST algorithm is O■, which is the same as the improved SST algorithm. In practical experiments, the running time of the generalized MSST algorithm is less than that of the improved SST algorithm.

关键词： Elliptic curve generalized AGM algorithm generalized MSST algorithm SST algorithm