arXiv subjects

Xiaoniu Yang

Publications and source records attributed to Xiaoniu Yang.

At least 37 records · Page 2Linked to original sources

arXiv2023

Deep Learning-Based Frequency Offset Estimation

In wireless communication systems, the asynchronization of the oscillators in the transmitter and the receiver along with the Doppler shift due to relative movement may lead to the presence of carrier frequency offset (CFO) in the received signals. Estimation of CFO is crucial for subsequent processing such as coherent demodulation. In this brief, we demonstrate the utilization of deep learning for CFO estimation by employing a residual network (ResNet) to learn and extract signal features from the raw in-phase (I) and quadrature (Q) components of the signals. We use multiple modulation schemes in the training set to make the trained model adaptable to multiple modulations or even new signals. In comparison to the commonly used traditional CFO estimation methods, our proposed IQ-ResNet method exhibits superior performance across various scenarios including different oversampling ratios, various signal lengths, and different channels

eess.SP↗

arXiv2023

Augmenting Radio Signals with Wavelet Transform for Deep Learning-Based Modulation Recognition

The use of deep learning for radio modulation recognition has become prevalent in recent years. This approach automatically extracts high-dimensional features from large datasets, facilitating the accurate classification of modulation schemes. However, in real-world scenarios, it may not be feasible to gather sufficient training data in advance. Data augmentation is a method used to increase the diversity and quantity of training dataset and to reduce data sparsity and imbalance. In this paper, we propose data augmentation methods that involve replacing detail coefficients decomposed by discrete wavelet transform for reconstructing to generate new samples and expand the training set. Different generation methods are used to generate replacement sequences. Simulation results indicate that our proposed methods significantly outperform the other augmentation methods.

cs.LG↗

arXiv2023

Can pre-trained models assist in dataset distillation?

Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training. Meanwhile, Pre-trained Models (PTMs) function as knowledge repositories, containing extensive information from the original dataset. This naturally raises a question: Can PTMs effectively transfer knowledge to synthetic datasets, guiding DD accurately? To this end, we conduct preliminary experiments, confirming the contribution of PTMs to DD. Afterwards, we systematically study different options in PTMs, including initialization parameters, model architecture, training epoch and domain knowledge, revealing that: 1) Increasing model diversity enhances the performance of synthetic datasets; 2) Sub-optimal models can also assist in DD and outperform well-trained ones in certain cases; 3) Domain-specific PTMs are not mandatory for DD, but a reasonable domain match is crucial. Finally, by selecting optimal options, we significantly improve the cross-architecture generalization over baseline DD methods. We hope our work will facilitate researchers to develop better DD techniques. Our code is available at https://github.com/yaolu-zjut/DDInterpreter.

cs.CV↗

arXiv2023

AIR: Threats of Adversarial Attacks on Deep Learning-Based Information Recovery

A wireless communications system usually consists of a transmitter which transmits the information and a receiver which recovers the original information from the received distorted signal. Deep learning (DL) has been used to improve the performance of the receiver in complicated channel environments and state-of-the-art (SOTA) performance has been achieved. However, its robustness has not been investigated. In order to evaluate the robustness of DL-based information recovery models under adversarial circumstances, we investigate adversarial attacks on the SOTA DL-based information recovery model, i.e., DeepReceiver. We formulate the problem as an optimization problem with power and peak-to-average power ratio (PAPR) constraints. We design different adversarial attack methods according to the adversary's knowledge of DeepReceiver's model and/or testing samples. Extensive experiments show that the DeepReceiver is vulnerable to the designed attack methods in all of the considered scenarios. Even in the scenario of both model and test sample restricted, the adversary can attack the DeepReceiver and increase its bit error rate (BER) above 10%. It can also be found that the DeepReceiver is vulnerable to adversarial perturbations even with very low power and limited PAPR. These results suggest that defense measures should be taken to enhance the robustness of DeepReceiver.

cs.CR↗

arXiv2022

TSGN: Transaction Subgraph Networks Assisting Phishing Detection in Ethereum

Due to the decentralized and public nature of the Blockchain ecosystem, the malicious activities on the Ethereum platform impose immeasurable losses for the users. Existing phishing scam detection methods mostly rely only on the analysis of original transaction networks, which is difficult to dig deeply into the transaction patterns hidden in the network structure of transaction interaction. In this paper, we propose a \underline{T}ransaction \underline{S}ub\underline{G}raph \underline{N}etwork (TSGN) based phishing accounts identification framework for Ethereum. We first extract transaction subgraphs for target accounts and then expand these subgraphs into corresponding TSGNs based on the different mapping mechanisms. In order to make our model incorporate more important information about real transactions, we encode the transaction attributes into the modeling process of TSGNs, yielding two variants of TSGN, i.e., Directed-TSGN and Temporal-TSGN, which can be applied to the different attributed networks. Especially, by introducing TSGN into multi-edge transaction networks, the Multiple-TSGN model proposed is able to preserve the temporal transaction flow information and capture the significant topological pattern of phishing scams, while reducing the time complexity of modeling large-scale networks. Extensive experimental results show that TSGN models can provide more potential information to improve the performance of phishing detection by incorporating graph representation learning.

cs.CR↗

arXiv2022

Understanding the Dynamics of DNNs Using Graph Modularity

There are good arguments to support the claim that deep neural networks (DNNs) capture better feature representations than the previous hand-crafted feature engineering, which leads to a significant performance improvement. In this paper, we move a tiny step towards understanding the dynamics of feature representations over layers. Specifically, we model the process of class separation of intermediate representations in pre-trained DNNs as the evolution of communities in dynamic graphs. Then, we introduce modularity, a generic metric in graph theory, to quantify the evolution of communities. In the preliminary experiment, we find that modularity roughly tends to increase as the layer goes deeper and the degradation and plateau arise when the model complexity is great relative to the dataset. Through an asymptotic analysis, we prove that modularity can be broadly used for different applications. For example, modularity provides new insights to quantify the difference between feature representations. More crucially, we demonstrate that the degradation and plateau in modularity curves represent redundant layers in DNNs and can be pruned with minimal impact on performance, which provides theoretical guidance for layer pruning. Our code is available at https://github.com/yaolu-zjut/Dynamic-Graphs-Construction.

cs.CV↗

arXiv2022

Graph-Based Similarity of Neural Network Representations

Understanding the black-box representations in Deep Neural Networks (DNN) is an essential problem in deep learning. In this work, we propose Graph-Based Similarity (GBS) to measure the similarity of layer features. Contrary to previous works that compute the similarity directly on the feature maps, GBS measures the correlation based on the graph constructed with hidden layer outputs. By treating each input sample as a node and the corresponding layer output similarity as edges, we construct the graph of DNN representations for each layer. The similarity between graphs of layers identifies the correspondences between representations of models trained in different datasets and initializations. We demonstrate and prove the invariance property of GBS, including invariance to orthogonal transformation and invariance to isotropic scaling, and compare GBS with CKA. GBS shows state-of-the-art performance in reflecting the similarity and provides insights on explaining the adversarial sample behavior on the hidden layer space.

cs.LG↗

arXiv2021

RGP: Neural Network Pruning through Its Regular Graph Structure

Lightweight model design has become an important direction in the application of deep learning technology, pruning is an effective mean to achieve a large reduction in model parameters and FLOPs. The existing neural network pruning methods mostly start from the importance of parameters, and design parameter evaluation metrics to perform parameter pruning iteratively. These methods are not studied from the perspective of model topology, may be effective but not efficient, and requires completely different pruning for different datasets. In this paper, we study the graph structure of the neural network, and propose regular graph based pruning (RGP) to perform a one-shot neural network pruning. We generate a regular graph, set the node degree value of the graph to meet the pruning ratio, and reduce the average shortest path length of the graph by swapping the edges to obtain the optimal edge distribution. Finally, the obtained graph is mapped into a neural network structure to realize pruning. Experiments show that the average shortest path length of the graph is negatively correlated with the classification accuracy of the corresponding neural network, and the proposed RGP shows a strong precision retention capability with extremely high parameter reduction (more than 90%) and FLOPs reduction (more than 90%).

cs.LG↗

arXiv2021

SigNet: A Novel Deep Learning Framework for Radio Signal Classification

Deep learning methods achieve great success in many areas due to their powerful feature extraction capabilities and end-to-end training mechanism, and recently they are also introduced for radio signal modulation classification. In this paper, we propose a novel deep learning framework called SigNet, where a signal-to-matrix (S2M) operator is adopted to convert the original signal into a square matrix first and is co-trained with a follow-up CNN architecture for classification. This model is further accelerated by integrating 1D convolution operators, leading to the upgraded model SigNet2.0. The simulations on two signal datasets show that both SigNet and SigNet2.0 outperform a number of well-known baselines. More interestingly, our proposed models behave extremely well in small-sample learning when only a small training dataset is provided. They can achieve a relatively high accuracy even when 1\% training data are kept, while other baseline models may lose their effectiveness much more quickly as the datasets get smaller. Such result suggests that SigNet/SigNet2.0 could be extremely useful in the situations where labeled signal data are difficult to obtain. The visualization of the output features of our models demonstrates that our model can well divide different modulation types of signals in the feature hyper-space.

eess.SP↗

arXiv2021

Deep Transfer Clustering of Radio Signals

Modulation recognition is an important task in radio signal processing. Most of the current researches focus on supervised learning. However, in many real scenarios, it is difficult and cost to obtain the labels of signals. In this letter, we turn to the more challenging problem: can we cluster the modulation types just based on a large number of unlabeled radio signals? If this problem can be solved, we then can also recognize modulation types by manually labeling a very small number of samples. To answer this problem, we propose a deep transfer clustering (DTC) model. DTC naturally integrates feature learning and deep clustering, and further adopts a transfer learning mechanism to improve the feature extraction ability of an embedded convolutional neural network (CNN) model. The experiments validate that our DTC significantly outperforms a number of baselines, achieving the state-of-the-art performance in clustering radio signals for modulation recognition.

eess.SP↗

arXiv2021

GGT: Graph-Guided Testing for Adversarial Sample Detection of Deep Neural Network

Deep Neural Networks (DNN) are known to be vulnerable to adversarial samples, the detection of which is crucial for the wide application of these DNN models. Recently, a number of deep testing methods in software engineering were proposed to find the vulnerability of DNN systems, and one of them, i.e., Model Mutation Testing (MMT), was used to successfully detect various adversarial samples generated by different kinds of adversarial attacks. However, the mutated models in MMT are always huge in number (e.g., over 100 models) and lack diversity (e.g., can be easily circumvented by high-confidence adversarial samples), which makes it less efficient in real applications and less effective in detecting high-confidence adversarial samples. In this study, we propose Graph-Guided Testing (GGT) for adversarial sample detection to overcome these aforementioned challenges. GGT generates pruned models with the guide of graph characteristics, each of them has only about 5% parameters of the mutated model in MMT, and graph guided models have higher diversity. The experiments on CIFAR10 and SVHN validate that GGT performs much better than MMT with respect to both effectiveness and efficiency.

cs.LG↗

arXiv2021

Adaptive Visibility Graph Neural Network and its Application in Modulation Classification

Our digital world is full of time series and graphs which capture the various aspects of many complex systems. Traditionally, there are respective methods in processing these two different types of data, e.g., Recurrent Neural Network (RNN) and Graph Neural Network (GNN), while in recent years, time series could be mapped to graphs by using the techniques such as Visibility Graph (VG), so that researchers can use graph algorithms to mine the knowledge in time series. Such mapping methods establish a bridge between time series and graphs, and have high potential to facilitate the analysis of various real-world time series. However, the VG method and its variants are just based on fixed rules and thus lack of flexibility, largely limiting their application in reality. In this paper, we propose an Adaptive Visibility Graph (AVG) algorithm that can adaptively map time series into graphs, based on which we further establish an end-to-end classification framework AVGNet, by utilizing GNN model DiffPool as the classifier. We then adopt AVGNet for radio signal modulation classification which is an important task in the field of wireless communication. The simulations validate that AVGNet outperforms a series of advanced deep learning methods, achieving the state-of-the-art performance in this task.

cs.LG↗

arXiv2021

CLPVG: Circular limited penetrable visibility graph as a new network model for time series

Visibility Graph (VG) transforms time series into graphs, facilitating signal processing by advanced graph data mining algorithms. In this paper, based on the classic Limited Penetrable Visibility Graph (LPVG) method, we propose a novel nonlinear mapping method named Circular Limited Penetrable Visibility Graph (CLPVG). The testing on degree distribution and clustering coefficient on the generated graphs of typical time series validates that our CLPVG is able to effectively capture the important features of time series and has better anti-noise ability than traditional LPVG. The experiments on real-world time-series datasets of radio signal and electroencephalogram (EEG) also suggest that the structural features provided by CLPVG, rather than LPVG, are more useful for time-series classification, leading to higher accuracy. And this classification performance can be further enhanced through structural feature expansion by adopting Subgraph Networks (SGN). All of these results validate the effectiveness of our CLPVG model.

cs.LG↗

arXiv2020

DemodNet: Learning Soft Demodulation from Hard Information Using Convolutional Neural Network

Soft demodulation is a basic module of traditional communication receivers. It converts received symbols into soft bits, that is, log likelihood ratios (LLRs). However, in the nonideal additive white Gaussian noise (AWGN) channel, it is difficult to accurately calculate the LLR. In this letter, we propose a demodulator, DemodNet, based on a fully convolutional neural network with variable input and output length. We use hard bit information to train the DemodNet, and we propose log probability ratio (LPR) based on the output layer of the trained DemodNet to realize soft demodulation. The simulation results show that under the AWGN channel, the performance of both hard demodulation and soft demodulation of DemodNet is very close to the traditional methods. In three non-ideal channel scenarios, i.e., the presence of frequency deviation, additive generalized Gaussian noise (AGGN) channel, and Rayleigh fading channel, the performance of channel decoding using the soft information LPR obtained by DemodNet is better than the performance of decoding using the exact LLR calculated under the ideal AWGN assumption.

eess.SP↗

arXiv2020

DeepReceiver: A Deep Learning-Based Intelligent Receiver for Wireless Communications in the Physical Layer

A canonical wireless communication system consists of a transmitter and a receiver. The information bit stream is transmitted after coding, modulation, and pulse shaping. Due to the effects of radio frequency (RF) impairments, channel fading, noise and interference, the signal arriving at the receiver will be distorted. The receiver needs to recover the original information from the distorted signal. In this paper, we propose a new receiver model, namely DeepReceiver, that uses a deep neural network to replace the traditional receiver's entire information recovery process. We design a one-dimensional convolution DenseNet (1D-Conv-DenseNet) structure, in which global pooling is used to improve the adaptability of the network to different input signal lengths. Multiple binary classifiers are used at the final classification layer to achieve multi-bit information stream recovery. We also exploit the DeepReceiver for unified blind reception of multiple modulation and coding schemes (MCSs) by including signal samples of corresponding MCSs in the training set. Simulation results show that the proposed DeepReceiver performs better than traditional step-by-step serial hard decision receiver in terms of bit error rate under the influence of various factors such as noise, RF impairments, multipath fading, cochannel interference, dynamic environment, and unified reception of multiple MCSs.

eess.SP↗

arXiv2019

Spectrum Sensing Based on Deep Learning Classification for Cognitive Radios

Spectrum sensing is a key technology for cognitive radios. We present spectrum sensing as a classification problem and propose a sensing method based on deep learning classification. We normalize the received signal power to overcome the effects of noise power uncertainty. We train the model with as many types of signals as possible as well as noise data to enable the trained network model to adapt to untrained new signals. We also use transfer learning strategies to improve the performance for real-world signals. Extensive experiments are conducted to evaluate the performance of this method. The simulation results show that the proposed method performs better than two traditional spectrum sensing methods, i.e., maximum-minimum eigenvalue ratio-based method and frequency domain entropy-based method. In addition, the experimental results of the new untrained signal types show that our method can adapt to the detection of these new signals. Furthermore, the real-world signal detection experiment results show that the detection performance can be further improved by transfer learning. Finally, experiments under colored noise show that our proposed method has superior detection performance under colored noise, while the traditional methods have a significant performance degradation, which further validate the superiority of our method.

eess.SP↗

arXiv2019

Deep Learning for Cooperative Radio Signal Classification

Radio signal classification has a very wide range of applications in cognitive radio networks and electromagnetic spectrum monitoring. In this article, we consider scenarios where multiple nodes in the network participate in cooperative classification. We propose cooperative radio signal classification methods based on deep learning for decision fusion, signal fusion and feature fusion, respectively. We analyze the performance of these methods through simulation experiments. We conclude the article with a discussion of research challenges and open problems.

eess.SP↗

arXiv2019

Open DNN Box by Power Side-Channel Attack

Deep neural networks are becoming popular and important assets of many AI companies. However, recent studies indicate that they are also vulnerable to adversarial attacks. Adversarial attacks can be either white-box or black-box. The white-box attacks assume full knowledge of the models while the black-box ones assume none. In general, revealing more internal information can enable much more powerful and efficient attacks. However, in most real-world applications, the internal information of embedded AI devices is unavailable, i.e., they are black-box. Therefore, in this work, we propose a side-channel information based technique to reveal the internal information of black-box models. Specifically, we have made the following contributions: (1) we are the first to use side-channel information to reveal internal network architecture in embedded devices; (2) we are the first to construct models for internal parameter estimation; and (3) we validate our methods on real-world devices and applications. The experimental results show that our method can achieve 96.50\% accuracy on average. Such results suggest that we should pay strong attention to the security problem of many AI applications, and further propose corresponding defensive strategies in the future.

cs.CR↗