Searcharxiv⌕ Search

arXiv subjects

Kai Zhou

Publications and source records attributed to Kai Zhou.

At least 109 records · Page 6Linked to original sources
arXiv2024

Machine learning study to identify collective flow in small and large colliding systems

Collective flow has been found to be similar between small colliding systems ($p$ $+$ $p$ and $p$ $+$ A collisions) and large colliding systems (peripheral A $+$ A collisions) at the CERN Large Hadron Collider. In order to study the differences of collective flow between small and large colliding systems, we employ a point cloud network to identify $p$ $+$ Pb collisions and peripheral Pb $+$ Pb collisions at $\sqrt{s_{NN}} =$ 5.02 TeV generated from a multiphase transport model (AMPT). After removing the discrepancies in the pseudorapidity distribution and the $p_{\rm T}$ spectra, we capture the discrepancy in collective flow. Although the verification accuracy of our PCN is limited due to similar event-by-event distributions of elliptic and triangular flow, we demonstrate that collective flow between $p$ $+$ Pb collisions and peripheral Pb $+$ Pb collisions becomes more distinct with increasing final hadron multiplicity and parton scattering cross section. This study not only highlights the potential of PCN techniques in advancing the understanding of collective flow in varying colliding systems, but more importantly lays the groundwork for the future PCN-related research.

nucl-th↗
arXiv2024

Reconstruction of partially occluded objects with a physics-driven self-training neural network

This study proposes a novel approach utilizing a physics-informed deep learning (DL) algorithm to reconstruct occluded objects in a terahertz (THz) holographic system. Taking the angular spectrum theory as prior knowledge, we generate a dataset consisting of a series of diffraction patterns that contain information about the objects. This dataset, combined with unlabeled data measured from experiments, are used for the self-training of a physics-informed neural network (NN). During the training process, the neural network iteratively predicts the outcomes of the unlabeled data and reincorporates these results back into the training set. This recursive strategy not only reduces noise but also minimizes mutual interference during object reconstruction, demonstrating its effectiveness even in data-scarce situations. The method has been validated with both simulated and experimental data, showcasing its significant potential to advance the field of terahertz three-dimensional (3D) imaging. Additionally, it sets a new benchmark for rapid, reference-free, and cost-effective power detection.

physics.optics↗
arXiv2024

Hybrid Multi-Head Physics-informed Neural Network for Depth Estimation in Terahertz Imaging

Terahertz (THz) imaging is one of the hotspots in the field of optics, where the depth information retrieval is a key factor to restore the three-dimensional appearance of objects. Impressive results for depth extraction in visible and infrared wave range have been demonstrated through deep learning (DL). Among them, most DL methods are merely data-driven, lacking relevant physical priors, which thus request for a large amount of experimental data to train the DL models.However, large training data acquirement in the THz domain is challenging due to the requirements of environmental and system stability, as well as the time-consuming data acquisition process. To overcome this limitation, this paper incorporates a complete physical model representing the THz image formation process into traditional DL networks to retrieve the depth information of objects. The most significant advantage is the ability to use it without pre-training, thereby eliminating the need for tens of thousands of labeled data. Through experiments validation, we demonstrate that by providing diffraction patterns of planar objects with their upper and lower halves individually masked, the proposed physics-informed neural network (NN) can automatically optimize and, ultimately, reconstruct the depth of the object through interaction between the NN and a physical model. The obtained results represent the initial steps towards achieving fast holographic THz imaging using reference-free beams and low-cost power detection.

physics.optics↗
arXiv2024

Diffusion Models as Stochastic Quantization in Lattice Field Theory

In this work, we establish a direct connection between generative diffusion models (DMs) and stochastic quantization (SQ). The DM is realized by approximating the reversal of a stochastic process dictated by the Langevin equation, generating samples from a prior distribution to effectively mimic the target distribution. Using numerical simulations, we demonstrate that the DM can serve as a global sampler for generating quantum lattice field configurations in two-dimensional $ϕ^4$ theory. We demonstrate that DMs can notably reduce autocorrelation times in the Markov chain, especially in the critical region where standard Markov Chain Monte-Carlo (MCMC) algorithms experience critical slowing down. The findings can potentially inspire further advancements in lattice field theory simulations, in particular in cases where it is expensive to generate large ensembles.

hep-lat↗
arXiv2024

Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices

Federated neuromorphic learning (FedNL) leverages event-driven spiking neural networks and federated learning frameworks to effectively execute intelligent analysis tasks over amounts of distributed low-power devices but also perform vulnerability to poisoning attacks. The threat of backdoor attacks on traditional deep neural networks typically comes from time-invariant data. However, in FedNL, unknown threats may be hidden in time-varying spike signals. In this paper, we start to explore a novel vulnerability of FedNL-based systems with the concept of time division multiplexing, termed Spikewhisper, which allows attackers to evade detection as much as possible, as multiple malicious clients can imperceptibly poison with different triggers at different timeslices. In particular, the stealthiness of Spikewhisper is derived from the time-domain divisibility of global triggers, in which each malicious client pastes only one local trigger to a certain timeslice in the neuromorphic sample, and also the polarity and motion of each local trigger can be configured by attackers. Extensive experiments based on two different neuromorphic datasets demonstrate that the attack success rate of Spikewispher is higher than the temporally centralized attacks. Besides, it is validated that the effect of Spikewispher is sensitive to the trigger duration.

cs.CR↗
arXiv2024

Collective Certified Robustness against Graph Injection Attacks

We investigate certified robustness for GNNs under graph injection attacks. Existing research only provides sample-wise certificates by verifying each node independently, leading to very limited certifying performance. In this paper, we present the first collective certificate, which certifies a set of target nodes simultaneously. To achieve it, we formulate the problem as a binary integer quadratic constrained linear programming (BQCLP). We further develop a customized linearization technique that allows us to relax the BQCLP into linear programming (LP) that can be efficiently solved. Through comprehensive experiments, we demonstrate that our collective certification scheme significantly improves certification performance with minimal computational overhead. For instance, by solving the LP within 1 minute on the Citeseer dataset, we achieve a significant increase in the certified ratio from 0.0% to 81.2% when the injected node number is 5% of the graph size. Our step marks a crucial step towards making provable defense more practical.

cs.CR↗
arXiv2024

Mass and tidal parameter extraction from gravitational waves of binary neutron stars mergers using deep learning

Gravitational Waves (GWs) from coalescing binaries carry crucial information about their component sources, like mass, spin and tidal effects. This implies that the analysis of GW signals from binary neutron star mergers can offer unique opportunities to extract information about the tidal properties of NSs, thereby adding constraints to the NS equation of state. In this work, we use Deep Learning (DL) techniques to overcome the computational challenges confronted in conventional methods of matched-filtering and Bayesian analyses for signal-detection and parameter-estimation. We devise a DL approach to classify GW signals from binary black hole and binary neutron star mergers. We further employ DL to analyze simulated GWs from binary neutron star merger events for parameter estimation, in particular, the regression of mass and tidal deformability of the component objects. The results presented in this work demonstrate the promising potential of DL techniques in GW analysis, paving the way for further advancement in this rapidly evolving field. The proposed approach is an efficient alternative to explore the wealth of information contained within GW signals of binary neutron star mergers, which can further help constrain the NS EoS.

astro-ph.HE↗
arXiv2024

Phase Transition Study meets Machine Learning

In recent years, machine learning (ML) techniques have emerged as powerful tools for studying many-body complex systems, and encompassing phase transitions in various domains of physics. This mini review provides a concise yet comprehensive examination of the advancements achieved in applying ML to investigate phase transitions, with a primary focus on those involved in nuclear matter studies.

nucl-th↗
arXiv2023

Cost Aware Untargeted Poisoning Attack against Graph Neural Networks,

Graph Neural Networks (GNNs) have become widely used in the field of graph mining. However, these networks are vulnerable to structural perturbations. While many research efforts have focused on analyzing vulnerability through poisoning attacks, we have identified an inefficiency in current attack losses. These losses steer the attack strategy towards modifying edges targeting misclassified nodes or resilient nodes, resulting in a waste of structural adversarial perturbation. To address this issue, we propose a novel attack loss framework called the Cost Aware Poisoning Attack (CA-attack) to improve the allocation of the attack budget by dynamically considering the classification margins of nodes. Specifically, it prioritizes nodes with smaller positive margins while postponing nodes with negative margins. Our experiments demonstrate that the proposed CA-attack significantly enhances existing attack strategies

cs.AI↗
arXiv2023

Node-aware Bi-smoothing: Certified Robustness against Graph Injection Attacks

Deep Graph Learning (DGL) has emerged as a crucial technique across various domains. However, recent studies have exposed vulnerabilities in DGL models, such as susceptibility to evasion and poisoning attacks. While empirical and provable robustness techniques have been developed to defend against graph modification attacks (GMAs), the problem of certified robustness against graph injection attacks (GIAs) remains largely unexplored. To bridge this gap, we introduce the node-aware bi-smoothing framework, which is the first certifiably robust approach for general node classification tasks against GIAs. Notably, the proposed node-aware bi-smoothing scheme is model-agnostic and is applicable for both evasion and poisoning attacks. Through rigorous theoretical analysis, we establish the certifiable conditions of our smoothing scheme. We also explore the practical implications of our node-aware bi-smoothing schemes in two contexts: as an empirical defense approach against real-world GIAs and in the context of recommendation systems. Furthermore, we extend two state-of-the-art certified robustness frameworks to address node injection attacks and compare our approach against them. Extensive evaluations demonstrate the effectiveness of our proposed certificates.

cs.LG↗
arXiv2023

Exploring QCD matter in extreme conditions with Machine Learning

In recent years, machine learning has emerged as a powerful computational tool and novel problem-solving perspective for physics, offering new avenues for studying strongly interacting QCD matter properties under extreme conditions. This review article aims to provide an overview of the current state of this intersection of fields, focusing on the application of machine learning to theoretical studies in high energy nuclear physics. It covers diverse aspects, including heavy ion collisions, lattice field theory, and neutron stars, and discuss how machine learning can be used to explore and facilitate the physics goals of understanding QCD matter. The review also provides a commonality overview from a methodology perspective, from data-driven perspective to physics-driven perspective. We conclude by discussing the challenges and future prospects of machine learning applications in high energy nuclear physics, also underscoring the importance of incorporating physics priors into the purely data-driven learning toolbox. This review highlights the critical role of machine learning as a valuable computational paradigm for advancing physics exploration in high energy nuclear physics.

hep-ph↗
arXiv2023

Optimal Power Flow in Highly Renewable Power System Based on Attention Neural Networks

The Optimal Power Flow (OPF) problem is pivotal for power system operations, guiding generator output and power distribution to meet demand at minimized costs, while adhering to physical and engineering constraints. The integration of renewable energy sources, like wind and solar, however, poses challenges due to their inherent variability. This variability, driven largely by changing weather conditions, demands frequent recalibrations of power settings, thus necessitating recurrent OPF resolutions. This task is daunting using traditional numerical methods, particularly for extensive power systems. In this work, we present a cutting-edge, physics-informed machine learning methodology, trained using imitation learning and historical European weather datasets. Our approach directly correlates electricity demand and weather patterns with power dispatch and generation, circumventing the iterative requirements of traditional OPF solvers. This offers a more expedient solution apt for real-time applications. Rigorous evaluations on aggregated European power systems validate our method's superiority over existing data-driven techniques in OPF solving. By presenting a quick, robust, and efficient solution, this research sets a new standard in real-time OPF resolution, paving the way for more resilient power systems in the era of renewable energy.

cs.LG↗
arXiv2023

QCD Equation of State of Dense Nuclear Matter from a Bayesian Analysis of Heavy-Ion Collision Data

Bayesian methods are used to constrain the density dependence of the QCD Equation of State (EoS) for dense nuclear matter using the data of mean transverse kinetic energy and elliptic flow of protons from heavy ion collisions (HIC), in the beam energy range $\sqrt{s_{\mathrm{NN}}}=2-10 GeV$. The analysis yields tight constraints on the density dependent EoS up to 4 times the nuclear saturation density. The extracted EoS yields good agreement with other observables measured in HIC experiments and constraints from astrophysical observations both of which were not used in the inference. The sensitivity of inference to the choice of observables is also discussed.

hep-ph↗
arXiv2023

Generative Diffusion Models for Lattice Field Theory

This study delves into the connection between machine learning and lattice field theory by linking generative diffusion models (DMs) with stochastic quantization, from a stochastic differential equation perspective. We show that DMs can be conceptualized by reversing a stochastic process driven by the Langevin equation, which then produces samples from an initial distribution to approximate the target distribution. In a toy model, we highlight the capability of DMs to learn effective actions. Furthermore, we demonstrate its feasibility to act as a global sampler for generating configurations in the two-dimensional $ϕ^4$ quantum lattice field theory.

hep-lat↗
arXiv2023

Resource-aware Research on Universe and Matter: Call-to-Action in Digital Transformation

Given the urgency to reduce fossil fuel energy production to make climate tipping points less likely, we call for resource-aware knowledge gain in the research areas on Universe and Matter with emphasis on the digital transformation. A portfolio of measures is described in detail and then summarized according to the timescales required for their implementation. The measures will both contribute to sustainable research and accelerate scientific progress through increased awareness of resource usage. This work is based on a three-days workshop on sustainability in digital transformation held in May 2023.

physics.comp-ph↗
arXiv2023

Coupled-Space Attacks against Random-Walk-based Anomaly Detection

Random Walks-based Anomaly Detection (RWAD) is commonly used to identify anomalous patterns in various applications. An intriguing characteristic of RWAD is that the input graph can either be pre-existing or constructed from raw features. Consequently, there are two potential attack surfaces against RWAD: graph-space attacks and feature-space attacks. In this paper, we explore this vulnerability by designing practical coupled-space attacks, investigating the interplay between graph-space and feature-space attacks. To this end, we conduct a thorough complexity analysis, proving that attacking RWAD is NP-hard. Then, we proceed to formulate the graph-space attack as a bi-level optimization problem and propose two strategies to solve it: alternative iteration (alterI-attack) or utilizing the closed-form solution of the random walk model (cf-attack). Finally, we utilize the results from the graph-space attacks as guidance to design more powerful feature-space attacks (i.e., graph-guided attacks). Comprehensive experiments demonstrate that our proposed attacks are effective in enabling the target nodes from RWAD with a limited attack budget. In addition, we conduct transfer attack experiments in a black-box setting, which show that our feature attack significantly decreases the anomaly scores of target nodes. Our study opens the door to studying the coupled-space attack against graph anomaly detection in which the graph space relies on the feature space.

cs.CR↗
arXiv2023

Model dependence of the number of participant nucleons and observable consequences in heavy-ion collisions

The centrality determination and the estimated fluctuations of number of participant nucleons $N_{part}$ in Au-Au collisions at 1.23 $A$GeV beam kinetic energy suffers from severe model dependencies. Comparing the Glauber Monte Carlo (MC) and UrQMD transport models, it is shown that $N_{part}$ is a strongly model dependant quantity. In addition, for any given centrality class, Glauber MC and UrQMD predicts drastically different $N_{part}$ distributions. The impact parameter $b$ and the number of charged particles $N_{ch}$ on the other hand are much more correlated and give an almost model independent centrality estimator. It is suggested that the total baryon number balance, from integrated rapidity distributions, can be used instead of $N_{part}$ in experiments. Preliminary HADES data show significant differences to both, UrQMD simulations and STAR data in this respect.

hep-ph↗
arXiv2023

A Generalized Beale-Kato-Majda Breakdown Criterion for the free-boundary problem in Euler Equations with Surface Tension

It is shown in Ferrari \cite{Ferrari-1993CMP} that if $[0, T^*)$ is the maximal time interval of existence of a smooth solution of the incompressible Euler equations in a bounded, simply-connected domain in $\mathbb{R}^3$, then $\int_0^{T^*}\|ω(t,\cdot)\|_{L^\infty}dt=+\infty$, where $ω$ is the vorticity of the flow. Ferrari's result generalizes the classical Beale-Kato-Majda \cite{BKM-1984CMP}'s breakdown criterion in the case of a bounded fluid domain. In this manuscript, we show a breakdown criterion for a smooth solution of the Euler equations describing the motion of an incompressible fluid in a bounded domain in $\mathbb{R}^3$ with a free surface boundary. The fluid is under the influence of surface tension. In addition, we show that our breakdown criterion reduces to the one proved by Ferrari \cite{Ferrari-1993CMP} when the free surface boundary is fixed. Specifically, the additional control norms on the moving boundary will either become trivial or stop showing up if the kinematic boundary condition on the moving boundary reduces to the slip boundary condition.

math.AP↗