arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 541 records · Page 30Linked to original sources

arXiv2024

Interpreting and Improving Attention From the Perspective of Large Kernel Convolution

Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computational resources poses challenges in data-scarce and resource-constrained scenarios. Moreover, traditional self-attention mechanisms lack inherent spatial inductive biases, making them suboptimal for modeling local features critical to tasks involving smaller datasets. In this work, we introduce Large Kernel Convolutional Attention (LKCA), a novel formulation that reinterprets attention operations as a single large-kernel convolution. This design unifies the strengths of convolutional architectures locality and translation invariance with the global context modeling capabilities of self-attention. By embedding these properties into a computationally efficient framework, LKCA addresses key limitations of traditional attention mechanisms. The proposed LKCA achieves competitive performance across various visual tasks, particularly in data-constrained settings. Experimental results on CIFAR-10, CIFAR-100, SVHN, and Tiny-ImageNet demonstrate its ability to excel in image classification, outperforming conventional attention mechanisms and vision transformers in compact model settings. These findings highlight the effectiveness of LKCA in bridging local and global feature modeling, offering a practical and robust solution for real-world applications with limited data and resources.

cs.CV↗

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

Privacy-preserving Robotic-based Multi-factor Authentication Scheme for Secure Automated Delivery System

Package delivery is a critical aspect of various industries, but it often incurs high financial costs and inefficiencies when relying solely on human resources. The last-mile transport problem, in particular, contributes significantly to the expenditure of human resources in major companies. Robot-based delivery systems have emerged as a potential solution for last-mile delivery to address this challenge. However, robotic delivery systems still face security and privacy issues, like impersonation, replay, man-in-the-middle attacks (MITM), unlinkability, and identity theft. In this context, we propose a privacy-preserving multi-factor authentication scheme specifically designed for robot delivery systems. Additionally, AI-assisted robotic delivery systems are susceptible to machine learning-based attacks (e.g. FGSM, PGD, etc.). We introduce the \emph{first} transformer-based audio-visual fusion defender to tackle this issue, which effectively provides resilience against adversarial samples. Furthermore, we provide a rigorous formal analysis of the proposed protocol and also analyse the protocol security using a popular symbolic proof tool called ProVerif and Scyther. Finally, we present a real-world implementation of the proposed robotic system with the computation cost and energy consumption analysis. Code and pre-trained models are available at: https://drive.google.com/drive/folders/18B2YbxtV0Pyj5RSFX-ZzCGtFOyorBHil

cs.CR↗

arXiv2024

Gapless dispersive continuum in a modulated quantum kagome antiferromagnet

The pursuit of quantum spin liquid (QSL) states in condensed matter physics has drawn attention to kagome antiferromagnets (AFM) where a two-dimensional corner-sharing network of triangles frustrates conventional magnetic orders. While quantum kagome AFMs based on Cu$^{2+}$ (3d$^9$, $s=\frac{1}{2}$) ions have been extensively studied, there is so far little work beyond copper-based systems. Here we present our bulk magnetization, specific heat and neutron scattering studies on single crystals of a new titanium fluoride Cs$_8$RbK$_3$Ti$_{12}$F$_{48}$ where Ti$^{3+}$ (3d$^1$, $s = \frac{1}{2}$) ions form a modulated quantum kagome antiferromagnet that does not order magnetically down to 1.5 K. Our comprehensive map of the dynamic response function $S(Q,\hbarω)$ acquired at 1.5 K where the heat capacity is T-linear reveals a dispersive continuum emanating from soft lines that extend along (100). The data indicate fractionalized spinon-like excitations with quasi-one-dimensional dispersion within a quasi-two-dimensional spin system.

cond-mat.str-el↗

arXiv2024

Ramification of complex magnetism in Nd$_2$Ir$_2$O$_7$ observed by Raman scattering spectroscopy

Using Raman scattering spectroscopy, we uncover a complex magnetic behavior of Nd$_2$Ir$_2$O$_7$ , which stands out among magnetic pyrochlores by the lowest temperature of the all-in-all-out (AIAO) Ir moments ordering ($T^\mathrm{N}_{\small\rm{Ir}}=33$~K) and the highest temperature at which AIAO order of rare-earth Nd ions is detected ($T^\mathrm{*}_{\small\rm{Nd}}$=15~K). Our findings suggest that in the temperature range between 15~K and 33~K, Nd magnetic moments exhibit strong fluctuations, possibly originating from spin ice behavior. This complex behavior emerges from the interplay of strong spin-orbit coupling, electronic correlations, and geometric frustration on two magnetic pyrochlore sublattices of Nd and Ir ions. The ordering of Ir magnetic moments is accompanied by an appearance of one-magnon Raman modes at 26.3 and 29.6 meV compatible with the AIAO order and of a broad mode at 14 meV, which could be associated with spinon continuum arising from Nd spin ice fluctuations. While two one-magnon excitations show minimal temperature evolution with decreasing temperature, the 14 meV mode shifts to higher frequencies as the temperature approaches a crossover to Nd AIAO order, broadens, and disappears below 15~K. An additional two-magnon excitation of the AIAO Nd order at around 33 meV appears in the spectra at low temperatures. These rather high energies of magnetic excitations of Nd moments make Nd$_2$Ir$_2$O$_7$ a particularly attractive playground to study the rare-earth magnetism on the pyrochlore lattice.

cond-mat.str-el↗

arXiv2024

LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance Representation

With the attention gained by camera-only 3D object detection in autonomous driving, methods based on Bird-Eye-View (BEV) representation especially derived from the forward view transformation paradigm, i.e., lift-splat-shoot (LSS), have recently seen significant progress. The BEV representation formulated by the frustum based on depth distribution prediction is ideal for learning the road structure and scene layout from multi-view images. However, to retain computational efficiency, the compressed BEV representation such as in resolution and axis is inevitably weak in retaining the individual geometric details, undermining the methodological generality and applicability. With this in mind, to compensate for the missing details and utilize multi-view geometry constraints, we propose LSSInst, a two-stage object detector incorporating BEV and instance representations in tandem. The proposed detector exploits fine-grained pixel-level features that can be flexibly integrated into existing LSS-based BEV networks. Having said that, due to the inherent gap between two representation spaces, we design the instance adaptor for the BEV-to-instance semantic coherence rather than pass the proposal naively. Extensive experiments demonstrated that our proposed framework is of excellent generalization ability and performance, which boosts the performances of modern LSS-based BEV perception methods without bells and whistles and outperforms current LSS-based state-of-the-art works on the large-scale nuScenes benchmark.

cs.CV↗

arXiv2024

Nonstationary functional time series forecasting

We propose a nonstationary functional time series forecasting method with an application to age-specific mortality rates observed over the years. The method begins by taking the first-order differencing and estimates its long-run covariance function. Through eigen-decomposition, we obtain a set of estimated functional principal components and their associated scores for the differenced series. These components allow us to reconstruct the original functional data and compute the residuals. To model the temporal patterns in the residuals, we again perform dynamic functional principal component analysis and extract its estimated principal components and the associated scores for the residuals. As a byproduct, we introduce a geometrically decaying weighted approach to assign higher weights to the most recent data than those from the distant past. Using the Swedish age-specific mortality rates from 1751 to 2022, we demonstrate that the weighted dynamic functional factor model can produce more accurate point and interval forecasts, particularly for male series exhibiting higher volatility.

stat.ME↗

arXiv2024

CHANG-ES XXXV: Cosmic Ray Transport and Magnetic Field Structure of NGC 3556 at 3 GHz

Radio halos of edge-on galaxies are crucial for investigating cosmic ray propagation and magnetic field structures in galactic environments. We present VLA C-configuration S-band (2--4 GHz) observations of the spiral galaxy NGC 3556, a target from the Continuum Halos in Nearby Galaxies - an EVLA Survey (CHANG-ES). We estimate the thermal contribution to the radio emission from a combination of the H$α$ and mid-IR data, and employ Rotation Measure Synthesis to reveal the magnetic field structures. In our data, NGC 3556 exhibits a box-like radio halo extending nearly 7 kpc from the galactic plane. The scale height of the total S-band intensity in the halo is $1.68\pm 0.29$ kpc, while that of the non-thermal intensity is $1.93\pm 0.28$ kpc. Fitting the data to a 1-D cosmic-ray transport model, we find advection to describe the cosmic-ray propagation within the halo better than diffusion, with advection speeds of $245 \pm 15$ km s$^{-1}$ and $205 \pm 25$ km s$^{-1}$ above and below the disk, respectively. The magnetic field is detected patchily across the galaxy, displaying a toroidal configuration in the rotation measure map. The mean equipartition magnetic field strength is approximately $8.3\ μ$G in the disk and $4.5\ μ$G in the halo. In addition, a bubble-like structure extends nearly 3~kpc into the southern halo, aligned with the polarized intensity and H$α$ image, suggestive of superwinds generated by recent star formation feedback in the nuclear region.

astro-ph.GA↗

arXiv2024

Membership Inference Attack against Long-Context Large Language Models

Recent advances in Large Language Models (LLMs) have enabled them to overcome their context window limitations, and demonstrate exceptional retrieval and reasoning capacities on longer context. Quesion-answering systems augmented with Long-Context Language Models (LCLMs) can automatically search massive external data and incorporate it into their contexts, enabling faithful predictions and reducing issues such as hallucinations and knowledge staleness. Existing studies targeting LCLMs mainly concentrate on addressing the so-called lost-in-the-middle problem or improving the inference effiencicy, leaving their privacy risks largely unexplored. In this paper, we aim to bridge this gap and argue that integrating all information into the long context makes it a repository of sensitive information, which often contains private data such as medical records or personal identities. We further investigate the membership privacy within LCLMs external context, with the aim of determining whether a given document or sequence is included in the LCLMs context. Our basic idea is that if a document lies in the context, it will exhibit a low generation loss or a high degree of semantic similarity to the contents generated by LCLMs. We for the first time propose six membership inference attack (MIA) strategies tailored for LCLMs and conduct extensive experiments on various popular models. Empirical results demonstrate that our attacks can accurately infer membership status in most cases, e.g., 90.66% attack F1-score on Multi-document QA datasets with LongChat-7b-v1.5-32k, highlighting significant risks of membership leakage within LCLMs input contexts. Furthermore, we examine the underlying reasons why LCLMs are susceptible to revealing such membership information.

cs.CL↗

arXiv2024

DiffLoRA: Generating Personalized Low-Rank Adaptation Weights with Diffusion

Personalized text-to-image generation has gained significant attention for its capability to generate high-fidelity portraits of specific identities conditioned on user-defined prompts. Existing methods typically involve test-time fine-tuning or incorporating an additional pre-trained branch. However, these approaches struggle to simultaneously address efficiency, identity fidelity, and the preservation of the model's original generative capabilities. In this paper, we propose DiffLoRA, an efficient method that leverages the diffusion model as a hypernetwork to predict personalized Low-Rank Adaptation (LoRA) weights based on the reference images. By incorporating these LoRA weights into the off-the-shelf text-to-image model, DiffLoRA enables zero-shot personalization during inference, eliminating the need for post-processing optimization. Moreover, we introduce a novel identity-oriented LoRA weights construction pipeline to facilitate the training process of DiffLoRA. The dataset generated through this pipeline enables DiffLoRA to produce consistently high-quality LoRA weights. Notably, the distinctive properties of the diffusion model enhance the generation of superior weights by employing probabilistic modeling to capture intricate structural patterns and thoroughly explore the weight space. Comprehensive experimental results demonstrate that DiffLoRA outperforms existing personalization approaches across multiple benchmarks, achieving both time efficiency and maintaining identity fidelity throughout the personalization process.

cs.CV↗

arXiv2024

RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images

In recent years, diffusion models have revolutionized visual generation, outperforming traditional frameworks like Generative Adversarial Networks (GANs). However, generating images of humans with realistic semantic parts, such as hands and faces, remains a significant challenge due to their intricate structural complexity. To address this issue, we propose a novel post-processing solution named RealisHuman. The RealisHuman framework operates in two stages. First, it generates realistic human parts, such as hands or faces, using the original malformed parts as references, ensuring consistent details with the original image. Second, it seamlessly integrates the rectified human parts back into their corresponding positions by repainting the surrounding areas to ensure smooth and realistic blending. The RealisHuman framework significantly enhances the realism of human generation, as demonstrated by notable improvements in both qualitative and quantitative metrics. Code is available at https://github.com/Wangbenzhi/RealisHuman.

cs.CV↗

arXiv2024

TomoGRAF: A Robust and Generalizable Reconstruction Network for Single-View Computed Tomography

Computed tomography (CT) provides high spatial resolution visualization of 3D structures for scientific and clinical applications. Traditional analytical/iterative CT reconstruction algorithms require hundreds of angular data samplings, a condition that may not be met in practice due to physical and mechanical limitations. Sparse view CT reconstruction has been proposed using constrained optimization and machine learning methods with varying success, less so for ultra-sparse view CT reconstruction with one to two views. Neural radiance field (NeRF) is a powerful tool for reconstructing and rendering 3D natural scenes from sparse views, but its direct application to 3D medical image reconstruction has been minimally successful due to the differences between optical and X-ray photon transportation. Here, we develop a novel TomoGRAF framework incorporating the unique X-ray transportation physics to reconstruct high-quality 3D volumes using ultra-sparse projections without prior. TomoGRAF captures the CT imaging geometry, simulates the X-ray casting and tracing process, and penalizes the difference between simulated and ground truth CT sub-volume during training. We evaluated the performance of TomoGRAF on an unseen dataset of distinct imaging characteristics from the training data and demonstrated a vast leap in performance compared with state-of-the-art deep learning and NeRF methods. TomoGRAF provides the first generalizable solution for image-guided radiotherapy and interventional radiology applications, where only one or a few X-ray views are available, but 3D volumetric information is desired.

eess.IV↗

arXiv2024

Early Prediction of Natural Gas Pipeline Leaks Using the MKTCN Model

Natural gas pipeline leaks pose severe risks, leading to substantial economic losses and potential hazards to human safety. In this study, we develop an accurate model for the early prediction of pipeline leaks. To the best of our knowledge, unlike previous anomaly detection, this is the first application to use internal pipeline data for early prediction of leaks. The modeling process addresses two main challenges: long-term dependencies and sample imbalance. First, we introduce a dilated convolution-based prediction model to capture long-term dependencies, as dilated convolution expands the model's receptive field without added computational cost. Second, to mitigate sample imbalance, we propose the MKTCN model, which incorporates the Kolmogorov-Arnold Network as the fully connected layer in a dilated convolution model, enhancing network generalization. Finally, we validate the MKTCN model through extensive experiments on two real-world datasets. Results demonstrate that MKTCN outperforms in generalization and classification, particularly under severe data imbalance, and effectively predicts leaks up to 5000 seconds in advance. Overall, the MKTCN model represents a significant advancement in early pipeline leak prediction, providing robust generalization and improved modeling of the long-term dependencies inherent in multi-dimensional time-series data.

cs.LG↗

arXiv2024

UKTF: Unified Knowledge Tracing Framework for Subjective and Objective Assessments

With the continuous deepening and development of the concept of smart education, learners' comprehensive development and individual needs have received increasing attention. However, traditional educational evaluation systems tend to assess learners' cognitive abilities solely through general test scores, failing to comprehensively consider their actual knowledge states. Knowledge tracing technology can establish knowledge state models based on learners' historical answer data, thereby enabling personalized assessment of learners. Nevertheless, current classical knowledge tracing models are primarily suited for objective test questions, while subjective test questions still confront challenges such as complex data representation, imperfect modeling, and the intricate and dynamic nature of knowledge states. Drawing on the application of knowledge tracing technology in education, this study aims to fully utilize examination data and proposes a unified knowledge tracing model that integrates both objective and subjective test questions. Recognizing the differences in question structure, assessment methods, and data characteristics between objective and subjective test questions, the model employs the same backbone network for training both types of questions. Simultaneously, it achieves knowledge tracing for subjective test questions by universally modifying the training approach of the baseline model, adding branch networks, and optimizing the method of question encoding. This study conducted multiple experiments on real datasets, and the results consistently demonstrate that the model effectively addresses knowledge tracing issues in both objective and subjective test question scenarios.

cs.CY↗

arXiv2024

Probing the He II re-Ionization ERa via Absorbing C IV Historical Yield (HIERACHY) II: Project Design, Current Status, and Examples of Initial Data Products

The He II reionization epoch is expected to take place at $z\sim3-5$. In this stage, the helium and metals in the inter-galactic medium (IGM) are further ionized with additional contributions from harder non-stellar sources, and some large-scale gravitationally bound systems approach virialization. The "Probing the He II re-Ionization ERa via Absorbing C IV Historical Yield (HIERACHY)" program utilizes high- and medium-resolution spectra of bright background quasars at $z\approx3.9-5.2$ to investigate Ly$α$, C IV, and other metal absorption lines during this epoch. Additionally, we employ narrow-band imaging to search for Ly$α$ emitters associated with C IV absorbers, alongside multi-wavelength observations to identify and study particularly intriguing cases. In this paper, we present the design of the HIERACHY program, its current status, major scientific goals, and examples of initial data products from completed Magellan/MIKE, MagE spectroscopy, and MDM imaging observations. We also provide a brief outlook on future multi-wavelength observations that may significantly impact the related science.

astro-ph.GA↗

arXiv2024

Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach

Graph neural networks (GNNs) have attracted considerable attention due to their diverse applications. However, the scarcity and quality limitations of graph data present challenges to their training process in practical settings. To facilitate the development of effective GNNs, companies and researchers often seek external collaboration. Yet, directly sharing data raises privacy concerns, motivating data owners to train GNNs on their private graphs and share the trained models. Unfortunately, these models may still inadvertently disclose sensitive properties of their training graphs (e.g., average default rate in a transaction network), leading to severe consequences for data owners. In this work, we study graph property inference attack to identify the risk of sensitive property information leakage from shared models. Existing approaches typically train numerous shadow models for developing such attack, which is computationally intensive and impractical. To address this issue, we propose an efficient graph property inference attack by leveraging model approximation techniques. Our method only requires training a small set of models on graphs, while generating a sufficient number of approximated shadow models for attacks. To enhance diversity while reducing errors in the approximated models, we apply edit distance to quantify the diversity within a group of approximated models and introduce a theoretically guaranteed criterion to evaluate each model's error. Subsequently, we propose a novel selection mechanism to ensure that the retained approximated models achieve high diversity and low error. Extensive experiments across six real-world scenarios demonstrate our method's substantial improvement, with average increases of 2.7% in attack accuracy and 4.1% in ROC-AUC, while being 6.5$\times$ faster compared to the best baseline.

cs.LG↗

arXiv2024

Design of Programmable Temperature Platform and its Pyroelectrocatalytic applications

The Si based TiO2 thin films were prepared via the combination both of Sol-Gel and Spin-Coating method. The films were sintered at 850 degrees Celsius for half an hour, and the resulting films were characterized by X-ray diffraction (XRD) and scanning electron microscopy (SEM) for their phase composition and microstructure. It was found that the films contained silicon, anatase phase, and unknown impurities. There were holes and micro-cracks on the surface of TiO2 films. A program-controllable hot-cold test chamber was successfully developed and used to study the catalytic performance of the thin film for the first time. The results showed that TiO2 thin films had the ability to degrade Rhodamine B dyes. The highest degradation rate of Rhodamine B achieved 37% after 48 cold-hot cycles. Our design and the experimental results presented in this paper strongly highlight the bright prospects of the thermoelectric properties of TiO2 and water environmental disinfection applications.

cond-mat.mtrl-sci↗

arXiv2024

Fi$^2$VTS: Time Series Forecasting Via Capturing Intra- and Inter-Variable Variations in the Frequency Domain

Time series forecasting (TSF) plays a crucial role in various applications, including medical monitoring and crop growth. Despite the advancements in deep learning methods for TSF, their capacity to predict long-term series remains constrained. This limitation arises from the failure to account for both intra- and inter-variable variations meanwhile. To mitigate this challenge, we introduce the Fi$^2$VBlock, which leverages a \textbf{F}requency domain perspective to capture \textbf{i}ntra- and \textbf{i}nter-variable \textbf{V}ariations. After transforming into the frequency domain via the Frequency Transform Module, the Frequency Cross Attention between the real and imaginary parts is designed to obtain enhanced frequency representations and capture intra-variable variations. Furthermore, Inception blocks are employed to integrate information, thus capturing correlations across different variables. Our backbone network, Fi$^2$VTS, employs a residual architecture by concatenating multiple Fi$^2$VBlocks, thereby preventing degradation issues. Theoretically, we demonstrate that Fi$^2$VTS achieves a substantial reduction in both time and memory complexity, decreasing from $\mathcal{O}(L^2)$ to $\mathcal{O}(L)$ per Fi$^2$VBlock computation. Empirical evaluations reveal that Fi$^2$VTS outperforms other baselines on two benchmark datasets. The implementation code is accessible at \url{https://github.com/HITshenrj/Fi2VTS}.

cs.AI↗