Searcharxiv⌕ Search

arXiv subjects

Xuemei Li

Publications and source records attributed to Xuemei Li.

27 records · Page 2Linked to original sources
arXiv2023

SecureBERT and LLAMA 2 Empowered Control Area Network Intrusion Detection and Classification

Numerous studies have proved their effective strength in detecting Control Area Network (CAN) attacks. In the realm of understanding the human semantic space, transformer-based models have demonstrated remarkable effectiveness. Leveraging pre-trained transformers has become a common strategy in various language-related tasks, enabling these models to grasp human semantics more comprehensively. To delve into the adaptability evaluation on pre-trained models for CAN intrusion detection, we have developed two distinct models: CAN-SecureBERT and CAN-LLAMA2. Notably, our CAN-LLAMA2 model surpasses the state-of-the-art models by achieving an exceptional performance 0.999993 in terms of balanced accuracy, precision detection rate, F1 score, and a remarkably low false alarm rate of 3.10e-6. Impressively, the false alarm rate is 52 times smaller than that of the leading model, MTH-IDS (Multitiered Hybrid Intrusion Detection System). Our study underscores the promise of employing a Large Language Model as the foundational model, while incorporating adapters for other cybersecurity-related tasks and maintaining the model's inherent language-related capabilities.

cs.CR↗
arXiv2023

MPR-Net:Multi-Scale Pattern Reproduction Guided Universality Time Series Interpretable Forecasting

Time series forecasting has received wide interest from existing research due to its broad applications and inherent challenging. The research challenge lies in identifying effective patterns in historical series and applying them to future forecasting. Advanced models based on point-wise connected MLP and Transformer architectures have strong fitting power, but their secondary computational complexity limits practicality. Additionally, those structures inherently disrupt the temporal order, reducing the information utilization and making the forecasting process uninterpretable. To solve these problems, this paper proposes a forecasting model, MPR-Net. It first adaptively decomposes multi-scale historical series patterns using convolution operation, then constructs a pattern extension forecasting method based on the prior knowledge of pattern reproduction, and finally reconstructs future patterns into future series using deconvolution operation. By leveraging the temporal dependencies present in the time series, MPR-Net not only achieves linear time complexity, but also makes the forecasting process interpretable. By carrying out sufficient experiments on more than ten real data sets of both short and long term forecasting tasks, MPR-Net achieves the state of the art forecasting performance, as well as good generalization and robustness performance.

cs.LG↗
arXiv2022

${W}^{2,p}$ Estimates for Elliptic Equations on $C^{1,α}$ Domains

In this paper, a new method is represented to investigate boundary $W^{2,p}$ estimates for elliptic equations, which is, roughly speaking, to derive boundary $W^{2,p}$ estimates from interior $W^{2,p}$ estimates by Whitney decomposition. Using it, $W^{2,p}$ estimates on $C^{1,α}$ domains are obtained for nondivergence form linear elliptic equations and further more, fully nonlinear elliptic equations are also considered.

math.AP↗
arXiv2021

Nondegeneracy of the positive solutions for critical nonlinear Hartree equation in $\R^6$

We prove that any positive solution for the critical nonlinear Hartree equation $$-\Laplacian\fct{u}{x} -\int_{\R^6} \frac{\abs{\fct{u}{y}}^2 }{ \abs{x-y}^4 }\odif{y} \,\fct{u}{x}=0,\qtq{} x\in\R^6.$$ is nondegenerate. Firstly, in terms of spherical harmonics, we show that the corresponding linear operator can be decomposed into a series of one dimensional linear operators. Secondly, by making use of the Perron-Frobenius property, we show that the kernel of each one dimensional linear operator is finite. Finally, we show that the kernel of the corresponding linear operator is the direct sum of the kernel of all one dimensional linear operators.

math.AP↗
arXiv2018

A KAM-Theorem for Persistence of Quasi-periodic Invariant Tori in Bifurcation Theory of Equilibrium Points

In this paper, we establish a KAM-theorem for ordinary differential equations with finitely differentiable vector fields and multiple degeneracies. The theorem can be used to deal with the persistence of quasi-periodic invariant tori in multiple Hopf and zero-multiple Hopf bifurcations, as well as their subordinate bifurcations, of equilibrium points of continuous dynamical systems.

math.DS↗
arXiv2017

Quasi-periodic solutions for differential equations with an elliptic-type degenerate equilibrium point under small perturbations

This work focuses on the existence of quasi-periodic solutions for ordinary and delay differential equations (ODEs and DDEs for short) with an elliptic-type degenerate equilibrium point under quasi-periodic perturbations. We prove that under appropriate hypotheses there exist quasi-periodic solutions for perturbed ODEs and DDEs near the equilibrium point for most parameter values, then apply these results to the delayed van der Pol's oscillator with zero-Hopf singularity.

math.DS↗
arXiv2012

Exceptional high Seebeck Coefficient and Gas-Flow-Induced Voltage in Multilayer Graphene

Monolayer graphene shows Seebeck coefficient several times and gas-flow-induced voltage twenty times higher than that of bulk graphite. Here we find that the Seebeck coefficient of multilayer graphene increases monotonically with increasing layer and reaches its peak value at hexa-layer ~77% higher than for monolayer and then decreases, although the electric resistance decreases monotonically with increasing layer. The flow-induced voltage is significantly higher in 2, 4, 5, 6, 7 layered graphene than in 1, 3, 8 layered one, against the prevailing view that it should be proportional to Seebeck coefficient. These thickness effects are also in sharp contrast to that in continuous aluminum nanofilms.

cond-mat.mes-hall↗
arXiv2011

Enhanced Gas-Flow-Induced Voltage in Graphene

We show by systemically experimental investigation that gas-flow-induced voltage in monolayer graphene is more than twenty times of that in bulk graphite. Examination over samples with sheet resistances ranging from 307 to 1600 Ω/sq shows that the induced voltage increase with the resistance and can be further improved by controlling the quality and doping level of graphene. The induced voltage is nearly independent of the substrate materials and can be well explained by the interplay of Bernoulli's principle and the carrier density dependent Seebeck coefficient. The results demonstrate that graphene has great potential for flow sensors and energy conversion devices.

cond-mat.mtrl-sci↗