arXiv subjects

Xun Yuan

Publications and source records attributed to Xun Yuan.

17 recordsLinked to original sources

arXiv2026

A physics-informed foundation model for quantitative diffusion MRI

Understanding the human brain requires access to its microscopic tissue architecture. Diffusion magnetic resonance imaging (MRI) provides the only noninvasive window into whole-brain microstructure in vivo, yet reliable quantitative mapping remains confined to specialized research settings requiring dense sampling and optimized acquisition protocols. To address this gap, we present a physics-informed generative microstructure network (PIGMENT) that learns a universal generative prior of human brain microstructure and adapts it zero-shot to each participant's measured data to recover subject-specific maps. Trained on 11375 scans spanning multiple sites, vendors, and field strengths, PIGMENT enabled reliable quantitative mapping for tensor, kurtosis, and NODDI models across external datasets from five independent centers. It remains effective where conventional fitting becomes unreliable, recovering meaningful maps from extremely sparse acquisitions while supporting downstream tractography and structural connectivity mapping. PIGMENT estimates demonstrated strong biological validity, preserving submillimeter cortical microarchitectural patterns and early-childhood white matter developmental trajectories from 10-fold accelerated scans. Furthermore, PIGMENT enables reliable quantitative tensor mapping on cost-efficient low-field systems and the extraction of tumor-related biomarkers using ultra-fast clinical protocols. Together, these results establish PIGMENT as a physics-informed foundation model that extends quantitative diffusion MRI into regimes traditionally too sparse, heterogeneous, or clinically constrained for reliable analysis.

eess.IV↗

arXiv2025

Towards Irreversible Machine Unlearning for Diffusion Models

Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models forget specific training data and prevent the generation of sensitive or unwanted content. Current machine unlearning methods for diffusion models are primarily designed for conditional diffusion models and focus on unlearning specific data classes or features. Among these methods, finetuning-based machine unlearning methods are recognized for their efficiency and effectiveness, which update the parameters of pre-trained diffusion models by minimizing carefully designed loss functions. However, in this paper, we propose a novel attack named Diffusion Model Relearning Attack (DiMRA), which can reverse the finetuning-based machine unlearning methods, posing a significant vulnerability of this kind of technique. Without prior knowledge of the unlearning elements, DiMRA optimizes the unlearned diffusion model on an auxiliary dataset to reverse the unlearning, enabling the model to regenerate previously unlearned elements. To mitigate this vulnerability, we propose a novel machine unlearning method for diffusion models, termed as Diffusion Model Unlearning by Memorization (DiMUM). Unlike traditional methods that focus on forgetting, DiMUM memorizes alternative data or features to replace targeted unlearning data or features in order to prevent generating such elements. In our experiments, we demonstrate the effectiveness of DiMRA in reversing state-of-the-art finetuning-based machine unlearning methods for diffusion models, highlighting the need for more robust solutions. We extensively evaluate DiMUM, demonstrating its superior ability to preserve the generative performance of diffusion models while enhancing robustness against DiMRA.

cs.LG↗

arXiv2024

Leveraging A New GAN-based Transformer with ECDH Crypto-system for Enhancing Energy Theft Detection in Smart Grid

Detecting energy theft is vital for effectively managing power grids, as it ensures precise billing and prevents financial losses. Split-learning emerges as a promising decentralized machine learning technique for identifying energy theft while preserving user data confidentiality. Nevertheless, traditional split learning approaches are vulnerable to privacy leakage attacks, which significantly threaten data confidentiality. To address this challenge, we propose a novel GAN-Transformer-based split learning framework in this paper. This framework leverages the strengths of the transformer architecture, which is known for its capability to process long-range dependencies in energy consumption data. Thus, it enhances the accuracy of energy theft detection without compromising user privacy. A distinctive feature of our approach is the deployment of a novel mask-based method, marking a first in its field to effectively combat privacy leakage in split learning scenarios targeted at AI-enabled adversaries. This method protects sensitive information during the model's training phase. Our experimental evaluations indicate that the proposed framework not only achieves accuracy levels comparable to conventional methods but also significantly enhances privacy protection. The results underscore the potential of the GAN-Transformer split learning framework as an effective and secure tool in the domain of energy theft detection.

cs.CR↗

arXiv2024

VFLGAN-TS: Vertical Federated Learning-based Generative Adversarial Networks for Publication of Vertically Partitioned Time-Series Data

In the current artificial intelligence (AI) era, the scale and quality of the dataset play a crucial role in training a high-quality AI model. However, often original data cannot be shared due to privacy concerns and regulations. A potential solution is to release a synthetic dataset with a similar distribution to the private dataset. Nevertheless, in some scenarios, the attributes required to train an AI model are distributed among different parties, and the parties cannot share the local data for synthetic data construction due to privacy regulations. In PETS 2024, we recently introduced the first Vertical Federated Learning-based Generative Adversarial Network (VFLGAN) for publishing vertically partitioned static data. However, VFLGAN cannot effectively handle time-series data, presenting both temporal and attribute dimensions. In this article, we proposed VFLGAN-TS, which combines the ideas of attribute discriminator and vertical federated learning to generate synthetic time-series data in the vertically partitioned scenario. The performance of VFLGAN-TS is close to that of its counterpart, which is trained in a centralized manner and represents the upper limit for VFLGAN-TS. To further protect privacy, we apply a Gaussian mechanism to make VFLGAN-TS satisfy an $(ε,δ)$-differential privacy. Besides, we develop an enhanced privacy auditing scheme to evaluate the potential privacy breach through the framework of VFLGAN-TS and synthetic datasets.

cs.LG↗

arXiv2024

MSADM: Large Language Model (LLM) Assisted End-to-End Network Health Management Based on Multi-Scale Semanticization

Network device and system health management is the foundation of modern network operations and maintenance. Traditional health management methods, relying on expert identification or simple rule-based algorithms, struggle to cope with the heterogeneous networks (HNs) environment. Moreover, current state-of-the-art distributed fault diagnosis methods, which utilize specific machine learning techniques, lack multi-scale adaptivity for heterogeneous device information, resulting in unsatisfactory diagnostic accuracy for HNs. In this paper, we develop an LLM-assisted end-to-end intelligent network health management framework. The framework first proposes a multi-scale data scaling method based on unsupervised learning to address the multi-scale data problem in HNs. Secondly, we combine the semantic rule tree with the attention mechanism to propose a Multi-Scale Semanticized Anomaly Detection Model (MSADM) that generates network semantic information while detecting anomalies. Finally, we embed a chain-of-thought-based large-scale language model downstream to adaptively analyze the fault diagnosis results and create an analysis report containing detailed fault information and optimization strategies. We compare our scheme with other fault diagnosis models and demonstrate that it performs well on several metrics of network fault diagnosis.

cs.NI↗

arXiv2024

VFLGAN: Vertical Federated Learning-based Generative Adversarial Network for Vertically Partitioned Data Publication

In the current artificial intelligence (AI) era, the scale and quality of the dataset play a crucial role in training a high-quality AI model. However, good data is not a free lunch and is always hard to access due to privacy regulations like the General Data Protection Regulation (GDPR). A potential solution is to release a synthetic dataset with a similar distribution to that of the private dataset. Nevertheless, in some scenarios, it has been found that the attributes needed to train an AI model belong to different parties, and they cannot share the raw data for synthetic data publication due to privacy regulations. In PETS 2023, Xue et al. proposed the first generative adversary network-based model, VertiGAN, for vertically partitioned data publication. However, after thoroughly investigating, we found that VertiGAN is less effective in preserving the correlation among the attributes of different parties. This article proposes a Vertical Federated Learning-based Generative Adversarial Network, VFLGAN, for vertically partitioned data publication to address the above issues. Our experimental results show that compared with VertiGAN, VFLGAN significantly improves the quality of synthetic data. Taking the MNIST dataset as an example, the quality of the synthetic dataset generated by VFLGAN is 3.2 times better than that generated by VertiGAN w.r.t. the Fréchet Distance. We also designed a more efficient and effective Gaussian mechanism for the proposed VFLGAN to provide the synthetic dataset with a differential privacy guarantee. On the other hand, differential privacy only gives the upper bound of the worst-case privacy guarantee. This article also proposes a practical auditing scheme that applies membership inference attacks to estimate privacy leakage through the synthetic dataset.

cs.LG↗

arXiv2024

A Novel DDPM-based Ensemble Approach for Energy Theft Detection in Smart Grids

Energy theft, characterized by manipulating energy consumption readings to reduce payments, poses a dual threat-causing financial losses for grid operators and undermining the performance of smart grids. Effective Energy Theft Detection (ETD) methods become crucial in mitigating these risks by identifying such fraudulent activities in their early stages. However, the majority of current ETD methods rely on supervised learning, which is hindered by the difficulty of labelling data and the risk of overfitting known attacks. To address these challenges, several unsupervised ETD methods have been proposed, focusing on learning the normal patterns from honest users, specifically the reconstruction of input. However, our investigation reveals a limitation in current unsupervised ETD methods, as they can only detect anomalous behaviours in users exhibiting regular patterns. Users with high-variance behaviours pose a challenge to these methods. In response, this paper introduces a Denoising Diffusion Probabilistic Model (DDPM)-based ETD approach. This innovative approach demonstrates impressive ETD performance on high-variance smart grid data by incorporating additional attributes correlated with energy consumption. The proposed methods improve the average ETD performance on high-variance smart grid data from below 0.5 to over 0.9 w.r.t. AUC. On the other hand, our experimental findings indicate that while the state-of-the-art ETD methods based on reconstruction error can identify ETD attacks for the majority of users, they prove ineffective in detecting attacks for certain users. To address this, we propose a novel ensemble approach that considers both reconstruction error and forecasting error, enhancing the robustness of the ETD methodology. The proposed ensemble method improves the average ETD performance on the stealthiest attacks from nearly 0 to 0.5 w.r.t. 5%-TPR.

cs.LG↗

arXiv2023

Chiral photonic topological states in Penrose quasicrystals

Electromagnetic topological edge states typically are created in photonic systems with crystalline symmetry and these states emerge because of the topological feature of bulk Bloch bands in momentum space according to the bulk-edge correspondence principle. In this work, we demonstrate the existence of chiral topological electromagnetic edge states in Penrose-tiled photonic quasicrystals made of magneto-optical materials, without relying on the concept of bulk Bloch bands in momentum space. Despite the absence of bulk Bloch bands, which naturally defiles the conventional definition of topological invariants in momentum space characterizing these states, such as the Chern number, we show that some bandgaps in these photonic quasicrystals still could host unidirectional topological electromagnetic edge states immune to backscattering in both cylinders-in-air and holes-in-slab configurations. Employing a real-space topological invariant based on the Bott index, our calculations reveal that the bandgaps hosting these chiral topological edge states possess a nontrivial Bott index of $\pm 1$, depending on the direction of the external magnetic field. Our work opens the door to the study of topological states in photonic quasicrystals.

physics.optics↗

arXiv2022

Using Chatbots to Teach Languages

This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners. Our system can adapt to users' language proficiency on the fly. We also provide automatic grammar error feedback to help users learn from their mistakes. According to our first adopters, our system is entertaining and useful. Furthermore, we will provide the learning technology community a large-scale conversation dataset on language learning and grammar correction. Our next step is to make our system more adaptive to user profile information by using reinforcement learning algorithms.

cs.CL↗

arXiv2022

ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error Correction

Currently available grammatical error correction (GEC) datasets are compiled using well-formed written text, limiting the applicability of these datasets to other domains such as informal writing and dialog. In this paper, we present a novel parallel GEC dataset drawn from open-domain chatbot conversations; this dataset is, to our knowledge, the first GEC dataset targeted to a conversational setting. To demonstrate the utility of the dataset, we use our annotated data to fine-tune a state-of-the-art GEC model, resulting in a 16 point increase in model precision. This is of particular importance in a GEC model, as model precision is considered more important than recall in GEC tasks since false positives could lead to serious confusion in language learners. We also present a detailed annotation scheme which ranks errors by perceived impact on comprehensibility, making our dataset both reproducible and extensible. Experimental results show the effectiveness of our data in improving GEC model performance in conversational scenario.

cs.CL↗

arXiv2020

Catalytically Potent and Selective Clusterzymes for Modulation of Neuroinflammation Through Single-Atom Substitutions

Emerging artificial enzymes with reprogrammed and augmented catalytic activity and substrate selectivity have long been pursued with sustained efforts. The majority of current candidates rely on noble metals or transition metal oxides with rather poor catalytic activity compared with natural molecules. To tackle this limitation, we strategically designed a novel artificial enzyme based on a structurally well-defined Au25 cluster, namely clusterzyme, which is endowed with intrinsic high catalytic activity and selectivity driven by single-atom substitutions with modulated bond lengths. The 3-mercaptopropionic acid (MPA)-stabilized Au24Cu1 and Au24Cd1 clusterzymes exhibit 137 and 160 times higher antioxidant capacities than the natural trolox, respectively. Meanwhile, the clusterzymes each demonstrate preferential enzyme-mimicking catalytic activities with compelling selectivity: Au25 exhibits superior glutathione peroxidase-like (GPx-like) activity; Au24Cu1 shows a distinct advantage towards catalase-like (CAT-like) activity by its Cu single active site; Au24Cd1 preferably acts as a superoxide dismutase-like (SOD-like) enzyme via the Cd single active site. This unique diversified catalytic landscape manifests distinctive reactions against inflammation in brain. Au24Cu1 behaves as an endogenous multi-enzyme mimic that directly decreases peroxide in injured brain via catalytic reactions, while Au24Cd1, catalyzes superoxide and nitrogenous signal molecules by preference, and significantly decreases inflammation factors such as IL-1\b{eta}, IL-6, and TNFα, indicative of an important role in mitigating neuroinflammation.

physics.bio-ph↗

arXiv2020

Realtime CNN-based Keypoint Detector with Sobel Filter and CNN-based Descriptor Trained with Keypoint Candidates

The local feature detector and descriptor are essential in many computer vision tasks, such as SLAM and 3D reconstruction. In this paper, we introduce two separate CNNs, lightweight SobelNet and DesNet, to detect key points and to compute dense local descriptors. The detector and the descriptor work in parallel. Sobel filter provides the edge structure of the input images as the input of CNN. The locations of key points will be obtained after exerting the non-maximum suppression (NMS) process on the output map of the CNN. We design Gaussian loss for the training process of SobelNet to detect corner points as keypoints. At the same time, the input of DesNet is the original grayscale image, and circle loss is used to train DesNet. Besides, output maps of SobelNet are needed while training DesNet. We have evaluated our method on several benchmarks including HPatches benchmark, ETH benchmark, and FM-Bench. SobelNet achieves better or comparable performance with less computation compared with SOTA methods in recent years. The inference time of an image of 640x480 is 7.59ms and 1.09ms for SobelNet and DesNet respectively on RTX 2070 SUPER.

cs.CV↗

arXiv2019

Identification of a monoclinic metallic state in VO2 from a modified first-principles approach

Metal-insulator transition underlies many remarkable and technologically important phenomena in VO2. Even though its monoclinic structure had before been the reserve of the insulating state, recent experiments have observed an unexpected monoclinic metallic state. Here we use a modified approach combining first-principles calculations with orbital-biased potentials to reproduce the correct stability ordering and electronic structure of different phases of VO2. We identify a ferromagnetic monoclinic metal that is likely to be the experimentally observed mysterious metastable state. Furthermore, our calculations show that an isostructural insulator-metal electronic transition is followed by the lattice distortion from the monoclinic structure to the rutile structure. These results not only explain the experimental observations of the monoclinic metallic state and the decoupled structural and electronic transitions of VO2, but also provide a understanding for the metal-insulator transition in other strongly correlated d electron systems.

cond-mat.str-el↗

arXiv2015

Ultrasmall Glutathione-Protected Gold Nanoclusters as Next Generation Radiotherapy Sensitizers with High Tumor Uptake and High Renal Clearance

Radiotherapy is often the most straightforward first line cancer treatment for solid tumors. While it is highly effective against tumors, there is also collateral damage to healthy proximal tissues especially with high doses. The use of radiosensitizers is an effective way to boost the killing efficacy of radiotherapy against the tumor while drastically limiting the received dose and reducing the possible damage to normal tissues. Here, we report the design and application of a good radiosensitizer by using ultrasmall gold nanoclusters with a naturally occurring peptide (e.g., glutathione or GSH) as the protecting shell. The GSH coated gold nanoclusters can escape the RES absorption, leading to a good tumor uptake (8.1% ID/g at 24 h post injection). As a result, the as-designed Au nanoclusters led to a strong enhancement for radiotherapy, as well as a negligible damage to normal tissues. After the treatment, the ultrasmall gold nanoclusters can be efficiently cleared by the kidney, thereby avoiding potential long term side effects caused by the accumulation of gold atoms in the body. Our data suggest that the ultrasmall peptide protected Au nanoclusters are a promising radiosensitizer for cancer radiotherapy.

physics.med-ph↗

arXiv2013

Hole-lattice Coupling and Photo-induced Insulator-Metal Transition in VO$_2$

Photo-induced insulator-metal transition in VO$_2$ and the related transient and multi-timescale structural dynamics upon photoexcitation are explained within a unified framework. Holes created by photoexcitation weaken the V-V bonds and eventually break V-V dimers in the M$_1$ phase of VO$_2$ when the laser fluence reaches a critical value. The breaking of the V-V bonds in turn leads to an immediate electronic phase transition from an insulating to a metallic state while the crystal lattice remains monoclinic in shape. The coupling between excited electrons and the 6.0 THz phonon mode is found to be responsible for the observed zig-zag motion of V atoms upon photoexcitation and is consistent with coherent phonon experiments.

cond-mat.mtrl-sci↗

arXiv2011

Comparative Study of Structural and Electronic Properties of Cu-based Multinary Semiconductors

We present a systematic and comparative study of the structural and electronic properties of Cu-based ternary and quaternary semiconductors using first-principles electronic structure approaches. The important role that Cu d electrons play in determining their properties is illustrated by comparing results calculated with different exchange correlation energy functionals. We show that systematic improvement of the calculated anion displacement can be achieved by using the Heyd-Scuseria-Ernzerhof (HSE06) functional compared with the Perdew-Burke-Ernzerhof (PBE) functional. Quasiparticle band structures are then calculated within the G0W0 approximation using the crystal structures optimized within the HSE06 functional and starting from the PBE+U mean-field solution. Both the calculated quasiparticle band gaps and their systematic variation with chemical constituents agree very well with experiments. We also predict that the quasiparticle band gaps of the prototypical semiconductor Cu2ZnSnS4 in the kesterite (KS) phase is 1.65 eV and that of the stannite (ST) phase is 1.40 eV. These results are also consistent with available experimental values which vary from 1.45 to 1.6 eV.

cond-mat.mtrl-sci↗

arXiv2008

Obtaining Exact Interpolation Multivariate Polynomial by Approximation

In some fields such as Mathematics Mechanization, automated reasoning and Trustworthy Computing etc., exact results are needed. Symbolic computations are used to obtain the exact results. Symbolic computations are of high complexity. In order to improve the situation, exactly interpolating methods are often proposed for the exact results and approximate interpolating methods for the approximate ones. In this paper, we study how to obtain exact interpolation polynomial with rational coefficients by approximate interpolating methods.

cs.SC↗