Searcharxiv⌕ Search

arXiv subjects

Kai Zhou

Publications and source records attributed to Kai Zhou.

At least 127 records · Page 7Linked to original sources
arXiv2023

Black-Box Attacks against Signed Graph Analysis via Balance Poisoning

Signed graphs are well-suited for modeling social networks as they capture both positive and negative relationships. Signed graph neural networks (SGNNs) are commonly employed to predict link signs (i.e., positive and negative) in such graphs due to their ability to handle the unique structure of signed graphs. However, real-world signed graphs are vulnerable to malicious attacks by manipulating edge relationships, and existing adversarial graph attack methods do not consider the specific structure of signed graphs. SGNNs often incorporate balance theory to effectively model the positive and negative links. Surprisingly, we find that the balance theory that they rely on can ironically be exploited as a black-box attack. In this paper, we propose a novel black-box attack called balance-attack that aims to decrease the balance degree of the signed graphs. We present an efficient heuristic algorithm to solve this NP-hard optimization problem. We conduct extensive experiments on five popular SGNN models and four real-world datasets to demonstrate the effectiveness and wide applicability of our proposed attack method. By addressing these challenges, our research contributes to a better understanding of the limitations and resilience of robust models when facing attacks on SGNNs. This work contributes to enhancing the security and reliability of signed graph analysis in social network modeling. Our PyTorch implementation of the attack is publicly available on GitHub: https://github.com/JialongZhou666/Balance-Attack.git.

cs.CR↗
arXiv2023

Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach

Graph anomaly detection (GAD) has achieved success and has been widely applied in various domains, such as fraud detection, cybersecurity, finance security, and biochemistry. However, existing graph anomaly detection algorithms focus on distinguishing individual entities (nodes or graphs) and overlook the possibility of anomalous groups within the graph. To address this limitation, this paper introduces a novel unsupervised framework for a new task called Group-level Graph Anomaly Detection (Gr-GAD). The proposed framework first employs a variant of Graph AutoEncoder (GAE) to locate anchor nodes that belong to potential anomaly groups by capturing long-range inconsistencies. Subsequently, group sampling is employed to sample candidate groups, which are then fed into the proposed Topology Pattern-based Graph Contrastive Learning (TPGCL) method. TPGCL utilizes the topology patterns of groups as clues to generate embeddings for each candidate group and thus distinct anomaly groups. The experimental results on both real-world and synthetic datasets demonstrate that the proposed framework shows superior performance in identifying and localizing anomaly groups, highlighting it as a promising solution for Gr-GAD. Datasets and codes of the proposed framework are at the github repository https://anonymous.4open.science/r/Topology-Pattern-Enhanced-Unsupervised-Group-level-Graph-Anomaly-Detection.

cs.LG↗
arXiv2023

Extension of Fujimoto's uniqueness theorems

Hirotaka Fujimoto considered two meromorphic maps $ f $ and $ g $ of $\mathbb{C}^m $ into $\mathbb{P}^n $ such that $ f^*(H_j)=g^*(H_j)$ ($ 1\leq j\leq q $) for $ q $ hyperplanes $ H_j $ in $\mathbb{P}^n $ in general position and proved $ f=g $ under suitable conditions. This paper considers the case where $ f $ is into $\mathbb{P}^n $ and $ g $ is into $\mathbb{P}^N $ and gives extensions of some of Fujimoto's uniqueness theorems. The dimensions $ N $ and $ n $ are proved to be equal under suitable conditions. New and interesting phenomena also occur.

math.CV↗
arXiv2023

A uniqueness theorem for meromorphic maps into $\mathbb{P}^n$ with generic $(2n+2)$ hyperplanes

Let $ H_1,\dots,H_{2n+2}$ be \emph{generic} $(2n+2)$ hyperplanes in $\mathbb{P}^n.$ It is proved that if meromorphic maps $ f $ and $ g $ of $\mathbb{C}^m $ into $\mathbb{P}^n $ satisfy $ f^*(H_j)=g^*(H_j)$ $(1\leq j\leq 2n+2)$ and $ g $ is algebraically non-degenerate then $ f=g.$ This result is essentially implied by the proof of Hirotaka Fujimoto in papers [Nagoya Math. J., 1976(64): 117--147] and [Nagoya Math. J., 1978(71): 13--24]. This note gives a complete proof of the above uniqueness result.

math.CV↗
arXiv2023

A note on Fujimoto's uniqueness theorem with $(2n+3)$ hyperplanes

Hirotaka Fujimoto proved in [Nagoya Math. J., 1976(64): 117--147] and [Nagoya Math. J., 1978(71): 13--24] a uniqueness theorem for algebraically non-degenerate meromorphic maps into $\mathbb{P}^n(\mathbb{C})$ sharing $(2n+3)$ hyperplanes in general position. The proof of Lemma 3.6 in [Nagoya Math. J., 1976(64): 117--147] is found to contain a mistake. This mistake can be corrected easily from a new point of view. This note explains the idea of the correction and provides a complete proof.

math.CV↗
arXiv2023

From Bi-Level to One-Level: A Framework for Structural Attacks to Graph Anomaly Detection

The success of graph neural networks stimulates the prosperity of graph mining and the corresponding downstream tasks including graph anomaly detection (GAD). However, it has been explored that those graph mining methods are vulnerable to structural manipulations on relational data. That is, the attacker can maliciously perturb the graph structures to assist the target nodes to evade anomaly detection. In this paper, we explore the structural vulnerability of two typical GAD systems: unsupervised FeXtra-based GAD and supervised GCN-based GAD. Specifically, structural poisoning attacks against GAD are formulated as complex bi-level optimization problems. Our first major contribution is then to transform the bi-level problem into one-level leveraging different regression methods. Furthermore, we propose a new way of utilizing gradient information to optimize the one-level optimization problem in the discrete domain. Comprehensive experiments demonstrate the effectiveness of our proposed attack algorithm BinarizedAttack.

cs.CR↗
arXiv2023

Towards Secrecy-Aware Attacks Against Trust Prediction in Signed Social Networks

Signed social networks are widely used to model the trust relationships among online users in security-sensitive systems such as cryptocurrency trading platforms, where trust prediction plays a critical role. In this paper, we investigate how attackers could mislead trust prediction by secretly manipulating signed networks. To this end, we first design effective poisoning attacks against representative trust prediction models. The attacks are formulated as hard bi-level optimization problems, for which we propose several efficient approximation solutions. However, the resulting basic attacks would severely change the structural semantics (in particular, both local and global balance properties) of a signed network, which makes the attacks prone to be detected by the powerful attack detectors we designed. Given this, we further refine the basic attacks by integrating some conflicting metrics as penalty terms into the objective function. The refined attacks become secrecy-aware, i.e., they can successfully evade attack detectors with high probability while sacrificing little attack performance. We conduct comprehensive experiments to demonstrate that the basic attacks can severely disrupt trust prediction but could be easily detected, and the refined attacks perform almost equally well while evading detection. Overall, our results significantly advance the knowledge in designing more practical attacks, reflecting more realistic threats to current trust prediction models. Moreover, the results also provide valuable insights and guidance for building up robust trust prediction systems.

cs.CR↗
arXiv2023

FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification

Graph Neural Networks (GNNs) are vulnerable to data poisoning attacks, which will generate a poisoned graph as the input to the GNN models. We present FocusedCleaner as a poisoned graph sanitizer to effectively identify the poison injected by attackers. Specifically, FocusedCleaner provides a sanitation framework consisting of two modules: bi-level structural learning and victim node detection. In particular, the structural learning module will reverse the attack process to steadily sanitize the graph while the detection module provides ``the focus" -- a narrowed and more accurate search region -- to structural learning. These two modules will operate in iterations and reinforce each other to sanitize a poisoned graph step by step. As an important application, we show that the adversarial robustness of GNNs trained over the sanitized graph for the node classification task is significantly improved. Extensive experiments demonstrate that FocusedCleaner outperforms the state-of-the-art baselines both on poisoned graph sanitation and improving robustness.

cs.LG↗
arXiv2023

SMTNet: Hierarchical cavitation intensity recognition based on sub-main transfer network

With the rapid development of smart manufacturing, data-driven machinery health management has been of growing attention. In situations where some classes are more difficult to be distinguished compared to others and where classes might be organised in a hierarchy of categories, current DL methods can not work well. In this study, a novel hierarchical cavitation intensity recognition framework using Sub-Main Transfer Network, termed SMTNet, is proposed to classify acoustic signals of valve cavitation. SMTNet model outputs multiple predictions ordered from coarse to fine along a network corresponding to a hierarchy of target cavitation states. Firstly, a data augmentation method based on Sliding Window with Fast Fourier Transform (Swin-FFT) is developed to solve few-shot problem. Secondly, a 1-D double hierarchical residual block (1-D DHRB) is presented to capture sensitive features of the frequency domain valve acoustic signals. Thirdly, hierarchical multi-label tree is proposed to assist the embedding of the semantic structure of target cavitation states into SMTNet. Fourthly, experience filtering mechanism is proposed to fully learn a prior knowledge of cavitation detection model. Finally, SMTNet has been evaluated on two cavitation datasets without noise (Dataset 1 and Dataset 2), and one cavitation dataset with real noise (Dataset 3) provided by SAMSON AG (Frankfurt). The prediction accurcies of SMTNet for cavitation intensity recognition are as high as 95.32%, 97.16% and 100%, respectively. At the same time, the testing accuracies of SMTNet for cavitation detection are as high as 97.02%, 97.64% and 100%. In addition, SMTNet has also been tested for different frequencies of samples and has achieved excellent results of the highest frequency of samples of mobile phones.

cs.SD↗
arXiv2023

Examination of nucleon distribution with Bayesian imaging for isobar collisions

Relativistic collision of isobaric systems is found to be valuable in differentiating the nucleon distributions for nuclei with the same mass number. In recent contrast experiment of $^{96}_{44}\text{Ru}+^{96}_{44}\text{Ru}$ versus $^{96}_{40}\text{Zr}+^{96}_{40}\text{Zr}$ collisions at $\sqrt{s_\text{NN}} = 200~\text{GeV}$, the ratios of multiplicity distribution, elliptic flow, triangular flow, and radial flow are precisely measured and found to be significantly different from unity, indicating the difference in the shapes of the isobar pair. In this work, we investigate the feasibility of nuclear structure reconstruction from heavy-ion collision observables. We perform Bayesian Inference with employing the Monte-Carlo Glauber model as an estimator of the mapping from nuclear structure to the final state observables and to provide the mock data for reconstruction. By varying combination of observables included in the mock data, we find it plausible to infer Woods--Saxon parameters from the observables. We also observe that single-system multiplicity distribution for the isobar system, rather than their ratio, is crucial to simultaneously determine the nuclear structure for the isobar system.

nucl-th↗
arXiv2023

Bottom energy loss and non-prompt $J/ψ$ production in relativistic heavy ion collisions

We study the momentum and centrality dependence of the non-prompt $J/ψ$ nuclear modification factors ($R_{AA}$), which comes from the $B$ hadrons decay, in Pb-Pb collisions at the Large Hadron Collider. Bottom quarks are produced in the parton hard scatterings and suffer energy loss in the quark-gluon plasma and the hadronic gas, where the spatial and time evolution of the medium is described with the hydrodynamic equations. Medium-induced elastic scatterings and the radiation in bottom quarks are included in the energy loss of bottom quarks. The hadronization process of bottom quarks is described with the instantaneous coalescence model. After considering both cold and hot nuclear matter effects in Pb-Pb collisions at $\sqrt{s_{NN}}=5.02$ TeV, we calculated the $R_{AA}$ and also the elliptic flows of non-prompt $J/ψ$ from the decay of $B$ mesons at different centralities and transverse momentum bins. The $R_{AA}$ and $v_2$ of non-prompt $J/ψ$ sensitive to the hot medium reflect and centrality supply an opportunity to study the bottom quarks energy loss in the hot medium.

nucl-th↗
arXiv2023

Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection

The robustness of recommender systems under node injection attacks has garnered significant attention. Recently, GraphRfi, a GNN-based recommender system, was proposed and shown to effectively mitigate the impact of injected fake users. However, we demonstrate that GraphRfi remains vulnerable to attacks due to the supervised nature of its fraudster detection component, where obtaining clean labels is challenging in practice. In particular, we propose a powerful poisoning attack, MetaC, against both GNN-based and MF-based recommender systems. Furthermore, we analyze why GraphRfi fails under such an attack. Then, based on our insights obtained from vulnerability analysis, we design an adaptive fraudster detection module that explicitly considers label uncertainty. This module can serve as a plug-in for different recommender systems, resulting in a robust framework named PDR. Comprehensive experiments show that our defense approach outperforms other benchmark methods under attacks. Overall, our research presents an effective framework for integrating fraudster detection into recommendation systems to achieve adversarial robustness.

cs.IR↗
arXiv2023

High energy nuclear physics meets Machine Learning

Though being seemingly disparate and with relatively new intersection, high energy nuclear physics and machine learning have already begun to merge and yield interesting results during the last few years. It's worthy to raise the profile of utilizing this novel mindset from machine learning in high energy nuclear physics, to help more interested readers see the breadth of activities around this intersection. The aim of this mini-review is to introduce to the community the current status and report an overview of applying machine learning for high energy nuclear physics, to present from different aspects and examples how scientific questions involved in high energy nuclear physics can be tackled using machine learning.

hep-ph↗
arXiv2023

The most frequent N-k line outages occur in motifs that can improve contingency selection

Multiple line outages that occur together show a variety of spatial patterns in the power transmission network. Some of these spatial patterns form network contingency motifs, which we define as the patterns of multiple outages that occur much more frequently than multiple outages chosen randomly from the network. We show that choosing N-k contingencies from these commonly occurring contingency motifs accounts for most of the probability of multiple initiating line outages. This result is demonstrated using historical outage data for two transmission systems. It enables N-k contingency lists that are much more efficient in accounting for the likely multiple initiating outages than exhaustive listing or random selection. The N-k contingency lists constructed from motifs can improve risk estimation in cascading outage simulations and help to confirm utility contingency selection.

physics.soc-ph↗
arXiv2023

Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks

A physics-informed neural network (PINN) embedded with the susceptible-infected-removed (SIR) model is devised to understand the temporal evolution dynamics of infectious diseases. Firstly, the effectiveness of this approach is demonstrated on synthetic data as generated from the numerical solution of the susceptible-asymptomatic-infected-recovered-dead (SAIRD) model. Then, the method is applied to COVID-19 data reported for Germany and shows that it can accurately identify and predict virus spread trends. The results indicate that an incomplete physics-informed model can approach more complicated dynamics efficiently. Thus, the present work demonstrates the high potential of using machine learning methods, e.g., PINNs, to study and predict epidemic dynamics in combination with compartmental models.

q-bio.QM↗
arXiv2023

Simple yet Effective Gradient-Free Graph Convolutional Networks

Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. Compared with nonlinear Graph Neural Network (GNN) models, linearized GNNs are much more time-efficient and can achieve comparable performances on typical downstream tasks such as node classification. Although some linearized GNN variants are purposely crafted to mitigate ``over-smoothing", empirical studies demonstrate that they still somehow suffer from this issue. In this paper, we instead relate over-smoothing with the vanishing gradient phenomenon and craft a gradient-free training framework to achieve more efficient and effective linearized GNNs which can significantly overcome over-smoothing and enhance the generalization of the model. The experimental results demonstrate that our methods achieve better and more stable performances on node classification tasks with varying depths and cost much less training time.

cs.LG↗
arXiv2022

Continuum-extrapolated NNLO Valence PDF of Pion at the Physical Point

We present lattice QCD calculations of valence parton distribution function (PDF) of pion employing next-to-next-leading-order (NNLO) perturbative QCD matching. Our calculations are based on three gauge ensembles of 2+1 flavor highly improved staggered quarks and Wilson--Clover valance quarks, corresponding to pion mass $m_π=140$~MeV at a lattice spacing $a=0.076$~fm and $m_π=300$~MeV at $a=0.04, 0.06$~fm. This enables us to present, for the first time, continuum-extrapolated lattice QCD results for NNLO valence PDF of the pion at the physical point. Applying leading-twist expansion for renormalization group invariant (RGI) ratios of bi-local pion matrix elements with NNLO Wilson coefficients we extract $2^{\mathrm{nd}}$, $4^{\mathrm{th}}$ and $6^{\mathrm{th}}$ Mellin moments of the PDF. We reconstruct the Bjorken-$x$ dependence of the NNLO PDF from real-space RGI ratios using a deep neural network (DNN) as well as from momentum-space matrix elements renormalized using a hybrid-scheme. All our results are in broad agreement with the results of global fits to the experimental data carried out by the xFitter and JAM collaborations.

hep-lat↗
arXiv2022

Reconstructing the neutron star equation of state from observational data via automatic differentiation

Neutron star observables like masses, radii, and tidal deformability are direct probes to the dense matter equation of state~(EoS). A novel deep learning method that optimizes an EoS in the automatic differentiation framework of solving inverse problems is presented. The trained neural network EoS yields narrow bands for the relationship between the pressure and speed of sound as a function of the mass density. The results are consistent with those obtained from conventional approaches and the observational bound on the tidal deformability inferred from the gravitational wave event, GW170817.

astro-ph.HE↗