arXiv subjects

Shi Tang

Publications and source records attributed to Shi Tang.

10 recordsLinked to original sources

arXiv2026

Algebraic Attack on Convolutional Neural Networks with Max Pooling

Recovering the weights and biases of deep neural networks (DNNs) via black-box input-output queries, known as parameter extraction attacks, has been extensively studied for ReLU-based fully connected neural networks (FCNNs), but remains unexplored for convolutional neural networks (CNNs) with the max pooling function, a core architecture for computer vision and multimedia processing. The key challenge lies in the CNN max pooling layer, which introduces an additional non-linearity and hides ReLU critical points, rendering existing FCNN extraction methods inapplicable. To address this gap, we propose the first cryptanalytic extraction attack tailored for CNNs with the max pooling function. First, we establish an algebraic representation of CNNs, formally proving that CNNs are piecewise linear functions enabling the extension of linearity-based extraction principles. We then identify two novel types of critical points in CNNs: ReLU-Pooling Critical Points (RPCPs) and Pooling Switching Points (PSPs). We design complementary extraction techniques: a pattern matching method for RPCPs to recover partial signatures and signs, and an internal differential extraction attack for PSPs, inspired by cryptographic internal differential analysis, to recover high-accuracy signatures. Given that PSPs are far more abundant than RPCPs and yield a highly efficient extraction method, and that RPCPs are indispensable for bias recovery, we integrate both methods: the PSP method enables efficient signature extraction, while a single RPCP recovers the sign and bias. We evaluate our attack on multiple CNN architectures, including modern adaptations of LeNet-5, trained on random data, MNIST, and CIFAR-10. Experimental results demonstrate that our approach achieves high extraction accuracy with polynomial query complexity and runtime, even for deep CNN layers. This work fills a research gap in CNN security.

cs.CR↗

arXiv2026

Algebraic Cryptanalytic Extraction on Hard-Label Neural Networks

Although the state-of-the-art neural network model extraction attack in the hard-label setting by Carlini et al. at EUROCRYPT 2025 has polynomial-time complexity in theory, its dual-point clustering relies on singular value decomposition (SVD) with a time complexity of $\mathcal{O}(n^2 \cdot (d^{(k)})^3)$, resulting in huge runtime in practice. To address this computational bottleneck, this work transforms Carlini et al.'s geometric-view hard-label attack into an algebraic framework, and proposes a novel Approximate Signature Vector (ASV) method to achieve efficient parameter extraction on Fully Connected Neural Networks (FCNNs) by leveraging two key observations: high-dimensional random vectors are nearly orthogonal, and neurons in practical DNNs tend to learn disentangled features. The proposed ASV method replaces SVD-based rank checking with simple inner-product operations, reducing the clustering complexity to $\mathcal{O}(n \cdot (d^{(k)})^3)$ on average. Furthermore, this paper presents the first model extraction attack against hard-label max-pooling Convolutional Neural Networks (CNNs) by proposing an advanced ASV method with a kernel-centric clustering scheme instead of the neuron-centric clustering, which fully exploits the property of weight sharing in convolutions and fills the cryptanalysis gap. Experiments on a 64-64$\times$4-10 FCNN and LeNet-5 (CNN) with max pooling demonstrate that our ASV method drastically cuts clustering time, and improves the overall efficiency in the model extraction.

cs.CR↗

arXiv2026

Round-Robin Test of a Light-Emitting Electrochemical Cell: Establishing a Reference Protocol for Quality Research

Emerging technologies benefit from a jointly established reference protocol, which can lower the bar of entry for new researchers while serving as a calibration standard for established actors. The light-emitting electrochemical cell (LEC) combines electrochemistry and optoelectronics in an intricate manner, and it can by that enable sustainable and commercially relevant printing fabrication of emissive thin-film devices. However, LEC performance is sensitive to a range of material and processing parameters, which frequently results in inadequate, or even erroneous, device evaluation. With this in mind, we present herein a LEC reference protocol, which details the sourcing of materials and the procedures and parameters for robust device fabrication and operation. The protocol has been tested across nine international research groups, and the collected results from this interlaboratory round-robin test confirm that good LEC performance can be reproducibly obtained following our protocol. We also identify common pitfalls that can arise during LEC development, and present practical steps for attaining optimum LEC performance. We hope this reference protocol will improve the quality of future LEC research and serve as a guide for future researchers entering this vibrant field.

cond-mat.soft↗

arXiv2025

EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation

Quantitative microstructural characterization is fundamental to materials science, and electron micrographs (EMs) provide indispensable high-resolution insights. However, progress in deep learning-based analysis of EMs has been hampered by the scarcity of large-scale, expert-annotated public datasets. To address this issue, we introduce EM3M, a large-scale and multimodal dataset for instance-level understanding of EMs. EM3M comprises 5,091 high-quality EMs, approximately 3 million instance segmentation annotations, and image-level textual descriptions with disentangled attributes. The dataset is constructed through a rigorous multi-stage curation and validation pipeline, with comprehensive statistical analyses to ensure reliability and reproducibility. Building upon these curated image-text pairs, we further provide a text-to-image diffusion model that serves as a controllable data augmentation engine, demonstrating that synthetic augmentation consistently improves downstream segmentation performance. To establish a systematic benchmark, we evaluate representative instance segmentation methods on EM3M. Our results reveal that conventional detection-based and query-based methods struggle with the extreme instance densities and textural complexities inherent in EMs. We additionally provide an optimized flow-based baseline to facilitate fair comparison and future research. EM3M {Dataset: https://huggingface.co/datasets/UniParser/EM3M}, the generative engine {Generation: https://huggingface.co/UniParser/EM3M-Gen}, and an online demo {Segmentation demo: https://www.bohrium.com/apps/uni-aims} are publicly available to support future research in automated materials analysis.

cs.CV↗

arXiv2025

Feature splitting parallel algorithm for Dantzig selectors

The Dantzig selector is a widely used and effective method for variable selection in ultra-high-dimensional data. Feature splitting is an efficient processing technique that involves dividing these ultra-high-dimensional variable datasets into manageable subsets that can be stored and processed more easily on a single machine. This paper proposes a variable splitting parallel algorithm for solving both convex and nonconvex Dantzig selectors based on the proximal point algorithm. The primary advantage of our parallel algorithm, compared to existing parallel approaches, is the significantly reduced number of iteration variables, which greatly enhances computational efficiency and accelerates the convergence speed of the algorithm. Furthermore, we show that our solution remains unchanged regardless of how the data is partitioned, a property referred to as partitioninsensitive. In theory, we use a concise proof framework to demonstrate that the algorithm exhibits linear convergence. Numerical experiments indicate that our algorithm performs competitively in both parallel and nonparallel environments. The R package for implementing the proposed algorithm can be obtained at https://github.com/xfwu1016/PPADS.

stat.CO↗

arXiv2024

Impact of the electrode material on the performance of light-emitting electrochemical cells

Light-emitting electrochemical cells (LECs) are promising candidates for fully solution-processed lighting applications because they can comprise a single active-material layer and air-stable electrodes. While their performance is often claimed to be independent of the electrode material selection due to the in-situ formation of electric double layers (EDLs), we demonstrate conceptually and experimentally that this understanding needs to be modified. Specifically, the exciton generation zone is observed to be affected by the electrode work function. We rationalize this finding by proposing that the ion concentration in the injection-facilitating EDLs depends on the offset between the electrode work function and the respective semiconductor orbital, which in turn influences the number of ions available for electrochemical doping and hence shifts the exciton generation zone. Further, we investigate the effects of the electrode selection on exciton losses to surface plasmon polaritons and discuss the impact of cavity effects on the exciton density. We conclude by showing that the measured electrode-dependent LEC luminance transients can be replicated by an optical model that considers these electrode-dependent effects to calculate the attained light outcoupling of the LEC stack. As such, our findings provide rational design criteria considering the electrode materials, the active-material thickness, and its composition in concert to achieve optimum LEC performance.

physics.optics↗

arXiv2024

A quasi-ohmic back contact achieved by inserting single-crystal graphene in flexible Kesterite solar cells

Flexible photovoltaics with a lightweight and adaptable nature that allows for deployment on curved surfaces and in building facades have always been a goal vigorously pursued by researchers in thin-film solar cell technology. The recent strides made in improving the sunlight-to-electricity conversion efficiency of kesterite Cu$_{2}$ZnSn(S, Se)$_{4}$ (CZTSSe) suggest it to be a perfect candidate. However, making use of rare Mo foil in CZTSSe solar cells causes severe problems in thermal expansion matching, uneven grain growth, and severe problems at the back contact of the devices. Herein, a strategy utilizing single-crystal graphene to modify the back interface of flexible CZTSSe solar cells is proposed. It will be shown that the insertion of graphene at the Mo foil/CZTSSe interface provides strong physical support for the subsequent deposition of the CZTSSe absorber layer, improving the adhesion between the absorber layer and the Mo foil substrate. Additionally, the graphene passivates the rough sites on the surface of the Mo foil, enhancing the chemical homogeneity of the substrate, and resulting in a more crystalline and homogeneous CZTSSe absorber layer on the Mo foil substrate. The detrimental reaction between Mo and CZTSSe has also been eliminated. Through an analysis of the electrical properties, it is found that the introduction of graphene at the back interface promotes the formation of a quasi-ohmic contact at the back contact, decreasing the back contact barrier of the solar cell, and leading to efficient collection of charges at the back interface. This investigation demonstrates that solution-based CZTSSe photovoltaic devices could form the basis of cheap and flexible solar cells.

cond-mat.mtrl-sci↗

arXiv2024

Harnessing the Power of Local Representations for Few-Shot Classification

Generalizing to novel classes unseen during training is a key challenge of few-shot classification. Recent metric-based methods try to address this by local representations. However, they are unable to take full advantage of them due to (i) improper supervision for pretraining the feature extractor, and (ii) lack of adaptability in the metric for handling various possible compositions of local feature sets. In this work, we harness the power of local representations in improving novel-class generalization. For the feature extractor, we design a novel pretraining paradigm that learns randomly cropped patches by soft labels. It utilizes the class-level diversity of patches while diminishing the impact of their semantic misalignments to hard labels. To align network output with soft labels, we also propose a UniCon KL-Divergence that emphasizes the equal contribution of each base class in describing "non-base" patches. For the metric, we formulate measuring local feature sets as an entropy-regularized optimal transport problem to introduce the ability to handle sets consisting of homogeneous elements. Furthermore, we design a Modulate Module to endow the metric with the necessary adaptability. Our method achieves new state-of-the-art performance on three popular benchmarks. Moreover, it exceeds state-of-the-art transductive and cross-modal methods in the fine-grained scenario.

cs.CV↗

arXiv2023

A study of simulating Raman spectra for alkanes with a machine learning-based polarizability model

Polarizability is closely related to many fundamental characteristics of molecular systems and plays an indispensable role in simulating the Raman spectra. However, the calculations of polarizability for large systems still suffers from the limitations of processing ability of the quantum mechanical (QM) methods. This work assessed and compared the accuracy of the bond polarizability model (BPM) and a ML-based atomic polarizability model (AlphaML) in predicting polarizability of alkanes and then also investigated the ability of simulating Raman spectra. We found that the AlphaML has appreciable advantages over the BPM in learning the polarizability in the training data set and predicting polarizability of molecules that configurational differently from training structures. In addition, the BPM has inherent disadvantages in predicting polarizability anisotropy due to many factors including large uncertainties of estimating bond anisotropy, omitting of off-diagonal parameters in the construction of the model. As a result, the BPM has larger errors than the AlphaML in the simulation of anisotropic Raman scattering. Finally, we demonstrated that both the BPM and AlphaML suffer from transference to alkanes larger than those used in the training data sets, but the problem for the AlphaML can be circumvented by exploring more proper training structures.

physics.chem-ph↗

arXiv2022

Electric field enhancement of pool boiling of dielectric fluids on pillar-structured surfaces: A lattice Boltzmann study

In this paper, by using a phase-change lattice Boltzmann (LB) model coupled with an electric field model, we numerically investigate the performance and enhancement mechanism of pool boiling of dielectric fluids on pillar-structured surfaces under an electric field. The numerical investigation reveals that applying an electric field causes both positive and negative influences on the pool boiling of dielectric fluids on pillar-structured surfaces. It is found that, under the action of an electric field, the electric force prevents the bubbles nucleated in the channels from crossing the edges of the pillar tops. On the one hand, such an effect results in the bubble coalescence in the channels and blocks the paths of liquid supply for the channels, which leads to the deterioration of pool boiling in the medium-superheat regime. On the other hand, it prevents the coalescence between the bubbles in the channels and those on the pillar tops, which suppresses the formation of a continuous vapor film and therefore delays the occurrence of boiling crisis. Meanwhile, the electric force can promote the departure of the bubbles on the pillar tops. Accordingly, the critical heat flux (CHF) can be improved. Based on the revealed mechanism, wettability-modified regions are applied to the pillar tops for further enhancing the boiling heat transfer. It is shown that the boiling performance on pillar-structured surfaces can be enhanced synergistically with the CHF being increased by imposing an electric field and the maximum heat transfer coefficient being improved by applying mixed wettability to the pillar-structured surfaces.

physics.flu-dyn↗