arXiv subjects

Qi Xuan

Publications and source records attributed to Qi Xuan.

At least 91 records · Page 5Linked to original sources

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

BufferSearch: Generating Black-Box Adversarial Texts With Lower Queries

Machine learning security has recently become a prominent topic in the natural language processing (NLP) area. The existing black-box adversarial attack suffers prohibitively from the high model querying complexity, resulting in easily being captured by anti-attack monitors. Meanwhile, how to eliminate redundant model queries is rarely explored. In this paper, we propose a query-efficient approach BufferSearch to effectively attack general intelligent NLP systems with the minimal number of querying requests. In general, BufferSearch makes use of historical information and conducts statistical test to avoid incurring model queries frequently. Numerically, we demonstrate the effectiveness of BufferSearch on various benchmark text-classification experiments by achieving the competitive attacking performance but with a significant reduction of query quantity. Furthermore, BufferSearch performs multiple times better than competitors within restricted query budget. Our work establishes a strong benchmark for the future study of query-efficiency in NLP adversarial attacks.

cs.CR↗

arXiv2023

Attacking The Assortativity Coefficient Under A Rewiring Strategy

Degree correlation is an important characteristic of networks, which is usually quantified by the assortativity coefficient. However, concerns arise about changing the assortativity coefficient of a network when networks suffer from adversarial attacks. In this paper, we analyze the factors that affect the assortativity coefficient and study the optimization problem of maximizing or minimizing the assortativity coefficient (r) in rewired networks with $k$ pairs of edges. We propose a greedy algorithm and formulate the optimization problem using integer programming to obtain the optimal solution for this problem. Through experiments, we demonstrate the reasonableness and effectiveness of our proposed algorithm. For example, rewired edges 10% in the ER network, the assortativity coefficient improved by 60%.

cs.SI↗

arXiv2023

RK-core: An Established Methodology for Exploring the Hierarchical Structure within Datasets

Recently, the field of machine learning has undergone a transition from model-centric to data-centric. The advancements in diverse learning tasks have been propelled by the accumulation of more extensive datasets, subsequently facilitating the training of larger models on these datasets. However, these datasets remain relatively under-explored. To this end, we introduce a pioneering approach known as RK-core, to empower gaining a deeper understanding of the intricate hierarchical structure within datasets. Across several benchmark datasets, we find that samples with low coreness values appear less representative of their respective categories, and conversely, those with high coreness values exhibit greater representativeness. Correspondingly, samples with high coreness values make a more substantial contribution to the performance in comparison to those with low coreness values. Building upon this, we further employ RK-core to analyze the hierarchical structure of samples with different coreset selection methods. Remarkably, we find that a high-quality coreset should exhibit hierarchical diversity instead of solely opting for representative samples. The code is available at https://github.com/yaolu-zjut/Kcore.

cs.LG↗

arXiv2023

Neighborhood Homophily-based Graph Convolutional Network

Graph neural networks (GNNs) have been proved powerful in graph-oriented tasks. However, many real-world graphs are heterophilous, challenging the homophily assumption of classical GNNs. To solve the universality problem, many studies deepen networks or concatenate intermediate representations, which does not inherently change neighbor aggregation and introduces noise. Recent studies propose new metrics to characterize the homophily, but rarely consider the correlation of the proposed metrics and models. In this paper, we first design a new metric, Neighborhood Homophily (\textit{NH}), to measure the label complexity or purity in node neighborhoods. Furthermore, we incorporate the metric into the classical graph convolutional network (GCN) architecture and propose \textbf{N}eighborhood \textbf{H}omophily-based \textbf{G}raph \textbf{C}onvolutional \textbf{N}etwork (\textbf{NHGCN}). In this framework, neighbors are grouped by estimated \textit{NH} values and aggregated from different channels, and the resulting node predictions are then used in turn to estimate and update \textit{NH} values. The two processes of metric estimation and model inference are alternately optimized to achieve better node classification. NHGCN achieves top overall performance on both homophilous and heterophilous benchmarks, with an improvement of up to 7.4\% compared to the current SOTA 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

Multi-triplet Feature Augmentation for Ponzi Scheme Detection in Ethereum

Blockchain technology revolutionizes the Internet, but also poses increasing risks, particularly in cryptocurrency finance. On the Ethereum platform, Ponzi schemes, phishing scams, and a variety of other frauds emerge. Existing Ponzi scheme detection approaches based on heterogeneous transaction graph modeling leverages semantic information between node (account) pairs to establish connections, overlooking the semantic attributes inherent to the edges (interactions). To overcome this, we construct heterogeneous Ethereum interaction graphs with multiple triplet interaction patterns to better depict the real Ethereum environment. Based on this, we design a new framework named multi-triplet augmented heterogeneous graph neural network (MAHGNN) for Ponzi scheme detection. We introduce the Conditional Variational Auto Encoder (CVAE) to capture the semantic information of different triplet interaction patterns, which facilitates the characterization on account features. Extensive experiments demonstrate that MAHGNN is capable of addressing the problem of multi-edge interactions in heterogeneous Ethereum interaction graphs and achieving state-of-the-art performance in Ponzi scheme detection.

cs.SI↗

arXiv2023

Inductive Subgraph Embedding for Link Prediction

Graph representation learning (GRL) has emerged as a powerful technique for solving graph analytics tasks. It can effectively convert discrete graph data into a low-dimensional space where the graph structural information and graph properties are maximumly preserved. While there is rich literature on node and whole-graph representation learning, GRL for link is relatively less studied and less understood. One common practice in previous works is to generate link representations by directly aggregating the representations of their incident nodes, which is not capable of capturing effective link features. Moreover, common GRL methods usually rely on full-graph training, suffering from poor scalability and high resource consumption on large-scale graphs. In this paper, we design Subgraph Contrastive Link Representation Learning (SCLRL) -- a self-supervised link embedding framework, which utilizes the strong correlation between central links and their neighborhood subgraphs to characterize links. We extract the "link-centric induced subgraphs" as input, with a subgraph-level contrastive discrimination as pretext task, to learn the intrinsic and structural link features via subgraph mini-batch training. Extensive experiments conducted on five datasets demonstrate that SCLRL has significant performance advantages in link representation learning on benchmark datasets and prominent efficiency advantages in terms of training speed and memory consumption on large-scale graphs, when compared with existing link representation learning methods.

cs.SI↗

arXiv2023

Photonic time-delayed reservoir computing based on series coupled microring resonators with high memory capacity

On-chip microring resonators (MRRs) have been proposed to construct the time-delayed reservoir computing (RC), which offers promising configurations available for computation with high scalability, high-density computing, and easy fabrication. A single MRR, however, is inadequate to supply enough memory for the computational task with diverse memory requirements. Large memory needs are met by the MRR with optical feedback waveguide, but at the expense of its large footprint. In the structure, the ultra-long optical feedback waveguide substantially limits the scalable photonic RC integrated designs. In this paper, a time-delayed RC is proposed by utilizing a silicon-based nonlinear MRR in conjunction with an array of linear MRRs. These linear MRRs possess a high quality factor, providing sufficient memory capacity for the entire system. We quantitatively analyze and assess the proposed RC structure's performance on three classical tasks with diverse memory requirements, i.e., the Narma 10, Mackey-Glass, and Santa Fe chaotic timeseries prediction tasks. The proposed system exhibits comparable performance to the MRR with an ultra-long optical feedback waveguide-based system when it comes to handling the Narma 10 task, which requires a significant memory capacity. Nevertheless, the overall length of these linear MRRs is significantly smaller, by three orders of magnitude, compared to the ultra-long feedback waveguide in the MRR with optical feedback waveguide-based system. The compactness of this structure has significant implications for the scalability and seamless integration of photonic RC.

physics.optics↗

arXiv2023

MONA: An Efficient and Scalable Strategy for Targeted k-Nodes Collapse

The concept of k-core plays an important role in measuring the cohesiveness and engagement of a network. And recent studies have shown the vulnerability of k-core under adversarial attacks. However, there are few researchers concentrating on the vulnerability of individual nodes within k-core. Therefore, in this paper, we attempt to study Targeted k-Nodes Collapse Problem (TNsCP), which focuses on removing a minimal size set of edges to make multiple target k-nodes collapse. For this purpose, we first propose a novel algorithm named MOD for candidate reduction. Then we introduce an efficient strategy named MONA, based on MOD, to address TNsCP. Extensive experiments validate the effectiveness and scalability of MONA compared to several baselines. An open-source implementation is available at https://github.com/Yocenly/MONA.

cs.SI↗

arXiv2023

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning

Graph neural networks (GNNs) have achieved remarkable success in various real-world applications. However, recent studies highlight the vulnerability of GNNs to malicious perturbations. Previous adversaries primarily focus on graph modifications or node injections to existing graphs, yielding promising results but with notable limitations. Graph modification attack~(GMA) requires manipulation of the original graph, which is often impractical, while graph injection attack~(GIA) necessitates training a surrogate model in the black-box setting, leading to significant performance degradation due to divergence between the surrogate architecture and the actual victim model. Furthermore, most methods concentrate on a single attack goal and lack a generalizable adversary to develop distinct attack strategies for diverse goals, thus limiting precise control over victim model behavior in real-world scenarios. To address these issues, we present a gradient-free generalizable adversary that injects a single malicious node to manipulate the classification result of a target node in the black-box evasion setting. We propose Gradient-free Generalizable Single Node Injection Attack, namely G$^2$-SNIA, a reinforcement learning framework employing Proximal Policy Optimization. By directly querying the victim model, G$^2$-SNIA learns patterns from exploration to achieve diverse attack goals with extremely limited attack budgets. Through comprehensive experiments over three acknowledged benchmark datasets and four prominent GNNs in the most challenging and realistic scenario, we demonstrate the superior performance of our proposed G$^2$-SNIA over the existing state-of-the-art baselines. Moreover, by comparing G$^2$-SNIA with multiple white-box evasion baselines, we confirm its capacity to generate solutions comparable to those of the best adversaries.

cs.LG↗

arXiv2023

SR-init: An interpretable layer pruning method

Despite the popularization of deep neural networks (DNNs) in many fields, it is still challenging to deploy state-of-the-art models to resource-constrained devices due to high computational overhead. Model pruning provides a feasible solution to the aforementioned challenges. However, the interpretation of existing pruning criteria is always overlooked. To counter this issue, we propose a novel layer pruning method by exploring the Stochastic Re-initialization. Our SR-init method is inspired by the discovery that the accuracy drop due to stochastic re-initialization of layer parameters differs in various layers. On the basis of this observation, we come up with a layer pruning criterion, i.e., those layers that are not sensitive to stochastic re-initialization (low accuracy drop) produce less contribution to the model and could be pruned with acceptable loss. Afterward, we experimentally verify the interpretability of SR-init via feature visualization. The visual explanation demonstrates that SR-init is theoretically feasible, thus we compare it with state-of-the-art methods to further evaluate its practicability. As for ResNet56 on CIFAR-10 and CIFAR-100, SR-init achieves a great reduction in parameters (63.98% and 37.71%) with an ignorable drop in top-1 accuracy (-0.56% and 0.8%). With ResNet50 on ImageNet, we achieve a 15.59% FLOPs reduction by removing 39.29% of the parameters, with only a drop of 0.6% in top-1 accuracy. Our code is available at https://github.com/huitang-zjut/SR-init.

cs.CV↗

arXiv2022

Targeted k-node Collapse Problem: Towards Understanding the Robustness of Local k-core Structure

The concept of k-core, which indicates the largest induced subgraph where each node has k or more neighbors, plays a significant role in measuring the cohesiveness and the engagement of a network, and it is exploited in diverse applications, e.g., network analysis, anomaly detection, community detection, etc. Recent works have demonstrated the vulnerability of k-core under malicious perturbations which focuses on removing the minimal number of edges to make a whole k-core structure collapse. However, to the best of our knowledge, there is no existing research concentrating on how many edges should be removed at least to make an arbitrary node in k-core collapse. Therefore, in this paper, we make the first attempt to study the Targeted k-node Collapse Problem (TNCP) with four novel contributions. Firstly, we offer the general definition of TNCP problem with the proof of its NP-hardness. Secondly, in order to address the TNCP problem, we propose a heuristic algorithm named TNC and its improved version named ATNC for implementations on large-scale networks. After that, the experiments on 16 real-world networks across various domains verify the superiority of our proposed algorithms over 4 baseline methods along with detailed comparisons and analyses. Finally, the significance of TNCP problem for precisely evaluating the resilience of k-core structures in networks is validated.

cs.SI↗

arXiv2022

Discover Important Paths in the Knowledge Graph Based on Dynamic Relation Confidence

Most of the existing knowledge graphs are not usually complete and can be complemented by some reasoning algorithms. The reasoning method based on path features is widely used in the field of knowledge graph reasoning and completion on account of that its have strong interpretability. However, reasoning methods based on path features still have several problems in the following aspects: Path search isinefficient, insufficient paths for sparse tasks and some paths are not helpful for reasoning tasks. In order to solve the above problems, this paper proposes a method called DC-Path that combines dynamic relation confidence and other indicators to evaluate path features, and then guide path search, finally conduct relation reasoning. Experimental result show that compared with the existing relation reasoning algorithm, this method can select the most representative features in the current reasoning task from the knowledge graph and achieve better performance on the current relation reasoning task.

cs.AI↗

arXiv2022

GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections

Graph neural networks (GNNs) have found successful applications in various graph-related tasks. However, recent studies have shown that many GNNs are vulnerable to adversarial attacks. In a vast majority of existing studies, adversarial attacks on GNNs are launched via direct modification of the original graph such as adding/removing links, which may not be applicable in practice. In this paper, we focus on a realistic attack operation via injecting fake nodes. The proposed Global Attack strategy via Node Injection (GANI) is designed under the comprehensive consideration of an unnoticeable perturbation setting from both structure and feature domains. Specifically, to make the node injections as imperceptible and effective as possible, we propose a sampling operation to determine the degree of the newly injected nodes, and then generate features and select neighbors for these injected nodes based on the statistical information of features and evolutionary perturbations obtained from a genetic algorithm, respectively. In particular, the proposed feature generation mechanism is suitable for both binary and continuous node features. Extensive experimental results on benchmark datasets against both general and defended GNNs show strong attack performance of GANI. Moreover, the imperceptibility analyses also demonstrate that GANI achieves a relatively unnoticeable injection on benchmark datasets.

cs.LG↗

arXiv2022

Behavior-aware Account De-anonymization on Ethereum Interaction Graph

Blockchain technology has the characteristics of decentralization, traceability and tamper-proof, which creates a reliable decentralized trust mechanism, further accelerating the development of blockchain finance. However, the anonymization of blockchain hinders market regulation, resulting in increasing illegal activities such as money laundering, gambling and phishing fraud on blockchain financial platforms. Thus, financial security has become a top priority in the blockchain ecosystem, calling for effective market regulation. In this paper, we consider identifying Ethereum accounts from a graph classification perspective, and propose an end-to-end graph neural network framework named Ethident, to characterize the behavior patterns of accounts and further achieve account de-anonymization. Specifically, we first construct an Account Interaction Graph (AIG) using raw Ethereum data. Then we design a hierarchical graph attention encoder named HGATE as the backbone of our framework, which can effectively characterize the node-level account features and subgraph-level behavior patterns. For alleviating account label scarcity, we further introduce contrastive self-supervision mechanism as regularization to jointly train our framework. Comprehensive experiments on Ethereum datasets demonstrate that our framework achieves superior performance in account identification, yielding 1.13% ~ 4.93% relative improvement over previous state-of-the-art. Furthermore, detailed analyses illustrate the effectiveness of Ethident in identifying and understanding the behavior of known participants in Ethereum (e.g. exchanges, miners, etc.), as well as that of the lawbreakers (e.g. phishing scammers, hackers, etc.), which may aid in risk assessment and market regulation.

cs.SI↗

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↗