arXiv subjects

Lei Zhou

Publications and source records attributed to Lei Zhou.

At least 55 records · Page 3Linked to original sources

arXiv2025

Learning Visual Proxy for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions by leveraging knowledge from seen compositions. Current methods align textual prototypes with visual features via Vision-Language Models (VLMs), but suffer from two limitations: (1) modality gaps hinder the discrimination of semantically similar pairs, and (2) single-modal textual prototypes lack fine-grained visual cues. In this paper, we introduce Visual Proxy Learning, a method that reduces modality gaps and enhances compositional generalization. We initialize visual proxies for attributes, objects, and their compositions using text representations and optimize the visual space to capture fine-grained cues, improving visual representations. Additionally, we propose Cross-Modal Joint Learning (CMJL), which imposes cross-modal constraints between the text-image and fine-grained visual spaces, improving generalization for unseen compositions and discriminating similar pairs. Experiments show state-of-the-art performance in closed-world scenarios and competitive results in open-world settings across four CZSL benchmarks, demonstrating the effectiveness of our approach in compositional generalization.

cs.CV↗

arXiv2025

Evolutionary dynamics under coordinated reciprocity

Using past behaviors to guide future actions is essential for fostering cooperation in repeated social dilemmas. Traditional memory-based strategies that focus on recent interactions have yielded valuable insights into the evolution of cooperative behavior. However, as memory length increases, the complexity of analysis grows exponentially, since these strategies need to map every possible action sequence of a given length to subsequent responses. Due to their inherent reliance on exhaustive mapping and a lack of explicit information processing, it remains unclear how individuals can handle extensive interaction histories to make decisions under cognitive constraints. To fill this gap, we introduce coordinated reciprocity strategies ($CORE$), which incrementally evaluate the entire game history by tallying instances of consistent actions between individuals without storing round-to-round details. Once this consistency index surpasses a threshold, $CORE$ prescribes cooperation. Through equilibrium analysis, we derive an analytical condition under which $CORE$ constitutes an equilibrium. Moreover, our numerical results show that $CORE$ effectively promotes cooperation between variants of itself, and it outperforms a range of existing strategies including memory-$1$, memory-$2$, and those from a documented strategy library in evolutionary dynamics. Our work thus underscores the pivotal role of cumulative action consistency in enhancing cooperation, developing robust strategies, and offering cognitively low-burden information processing mechanisms in repeated social dilemmas.

q-bio.PE↗

arXiv2025

Leveraging large language models for SQL behavior-based database intrusion detection

Database systems are extensively used to store critical data across various domains. However, the frequency of abnormal database access behaviors, such as database intrusion by internal and external attacks, continues to rise. Internal masqueraders often have greater organizational knowledge, making it easier to mimic employee behavior effectively. In contrast, external masqueraders may behave differently due to their lack of familiarity with the organization. Current approaches lack the granularity needed to detect anomalies at the operational level, frequently misclassifying entire sequences of operations as anomalies, even though most operations are likely to represent normal behavior. On the other hand, some anomalous behaviors often resemble normal activities, making them difficult for existing detection methods to identify. This paper introduces a two-tiered anomaly detection approach for Structured Query Language (SQL) using the Bidirectional Encoder Representations from Transformers (BERT) model, specifically DistilBERT, a more efficient, pre-trained version. Our method combines both unsupervised and supervised machine learning techniques to accurately identify anomalous activities while minimizing the need for data labeling. First, the unsupervised method uses ensemble anomaly detectors that flag embedding vectors distant from learned normal patterns of typical user behavior across the database (out-of-scope queries). Second, the supervised method uses fine-tuned transformer-based models to detect internal attacks with high precision (in-scope queries), using role-labeled classification, even on limited labeled SQL data. Our findings make a significant contribution by providing an effective solution for safeguarding critical database systems from sophisticated threats.

cs.CR↗

arXiv2025

Network Pharmacology Reveals HSPA1A/BST2 as Potential Targets of Ci Bai Capsule's Active Compounds Intervening in Leukopenia

Background: Radiation-induced leukopenia caused by low-dose exposure is frequently associated with Traditional Chinese Medicine (TCM) syndromes like "blood deficiency" and "fatigue syndrome". Ci Bai Capsule (CB) has been reported to enhance white blood cell levels; however, its mechanisms and bioactive compounds remain unclear.Aim: This study aimed to identify the bioactive compounds group of CB and elucidate its potential mechanisms in radiation-induced leukopenia.Methods: Syndrome-related data were gathered from SYMMAP and CTD database. CB's target profile is predicted by DrugCIPHER. Network pharmacology approaches were employed to identify active compounds and related pathways. Experimental validation was conducted through flow cytometry and RNA-sequencing in both ex vivo and in vivo models.Results: A total of 22 pathways related to cellular processes, immune responses, and signal transduction were identified. Five key bioactive compounds (kaempferol-3-glucorhamnoside, syringin, schisandrin, 3-hydroxytyrosol 3-O-glucoside and salidroside) were found to significantly modulate syndrome-related pathways. Optimal dosing of this compound combination enhanced leukocyte counts and splenic immune cell proliferation in irradiated mice. Transcriptomic analysis revealed that the compounds exert regulatory effects on PP1A, RB, CDK4/6, CDK2, and CDK1, thereby modulating downstream immune and hematopoietic markers such as MNDA, BST2, and HSPA1A.Conclusion: Our findings suggest that CB mitigates radiation-induced leukopenia by enhancing immune and hematopoietic recovery, offering a promising therapeutic approach for managing radiation-related hematological disorders.

q-bio.MN↗

arXiv2025

Non-Registration Change Detection: A Novel Change Detection Task and Benchmark Dataset

In this study, we propose a novel remote sensing change detection task, non-registration change detection, to address the increasing number of emergencies such as natural disasters, anthropogenic accidents, and military strikes. First, in light of the limited discourse on the issue of non-registration change detection, we systematically propose eight scenarios that could arise in the real world and potentially contribute to the occurrence of non-registration problems. Second, we develop distinct image transformation schemes tailored to various scenarios to convert the available registration change detection dataset into a non-registration version. Finally, we demonstrate that non-registration change detection can cause catastrophic damage to the state-of-the-art methods. Our code and dataset are available at https://github.com/ShanZard/NRCD.

cs.CV↗

arXiv2025

Overcoming Intrinsic Dispersion Locking for Achieving Spatio-Spectral Selectivity with Misaligned Bi-metagratings

Spatio-spectral selectivity, the capability to select a single mode with a specific wavevector (angle) and wavelength, is imperative for light emission and imaging. Continuous band dispersion of a conventional periodic structure, however, sets up an intrinsic locking between wavevectors and wavelengths of photonic modes, making it difficult to single out just one mode. Here, we show that the radiation asymmetry of a photonic mode can be explored to tailor the transmission/reflection properties of a photonic structure, based on Fano interferences between the mode and the background. In particular, we find that a photonic system supporting a band dispersion with certain angle-dependent radiation-directionality can exhibit Fano-like perfect reflection at a single frequency and a single incident angle, thus overcoming the dispersion locking and enabling the desired spatio-spectral selectivity. We present a phase diagram to guide designing angle-controlled radiation-directionality and experimentally demonstrate double narrow Fano-like reflection in angular (5°) and wavelength (14 nm) bandwidths, along with high-contrast spatio-spectral selective imaging, using a misaligned bilayer metagrating with tens-of-nanometer-scale thin spacer. Our scheme promises new opportunities in applications in directional thermal emission, nonlocal beam shaping, augmented reality, precision bilayer nanofabrication, and biological spectroscopy.

physics.optics↗

arXiv2025

Nonlinearity Modulation of Auto-oscillations in Three-terminal Magnetic Tunnel Junctions

Spin torque nano-oscillators (STNOs) hold encouraging promise for nanoscale microwave generators, modulators, and new types of intelligent computing. The nonlinearity, describing the current-induced tunability of oscillating frequency, is a distinctive feature of STNOs, which plays important roles in efficient manipulation of microwave frequencies, rapid spec-trum analysis, and the design of neuromorphic devices. However, experimental research on its efficient modulation remains limited. Here, we comprehensively studied the impact of several factors on nonlinearity in nanoscale three-terminal MTJ-STNOs, including the external magnetic field, the thickness of CoFeB free layer, and the combination of spin-transfer torque (STT) and spin-orbit torque (SOT). Among these factors, nonlinearity can be significantly tuned by the direction of magnetic field as well as the thickness of CoFeB free layer. Notably, it reaches zero in 1.1 nm CoFeB, where the oscillation frequency is not affected by the drive current. Such property provides a more intrinsic and robust approach to achieve zero nonlinearity in STNOs, which is advantageous for high-quality microwave generators. More importantly, we found that nonlinearity can also be electrically modulated by both STT and SOT currents, and develop a refined model that accounts for the additional contribution of the SOT current to explain the mechanism. This electrical approach is more convenient, energy-efficient, and well-suited for miniaturization. Our findings offer a comprehensive understanding and open up a new dimension for the current tunability of nonlinearity in MTJ-STNOs, benefiting further optimization in nanoscale STNO-based microwave generators and neuromorphic computing devices.

physics.app-ph↗

arXiv2025

Model Inversion Attack against Federated Unlearning

With the introduction of regulations related to the ``right to be forgotten", federated learning (FL) is facing new privacy compliance challenges. To address these challenges, researchers have proposed federated unlearning (FU). However, existing FU research has primarily focused on improving the efficiency of unlearning, with less attention paid to the potential privacy vulnerabilities inherent in these methods. To address this gap, we draw inspiration from gradient inversion attacks in FL and propose the federated unlearning inversion attack (FUIA). The FUIA is specifically designed for the three types of FU (sample unlearning, client unlearning, and class unlearning), aiming to provide a comprehensive analysis of the privacy leakage risks associated with FU. In FUIA, the server acts as an honest-but-curious attacker, recording and exploiting the model differences before and after unlearning to expose the features and labels of forgotten data. FUIA significantly leaks the privacy of forgotten data and can target all types of FU. This attack contradicts the goal of FU to eliminate specific data influence, instead exploiting its vulnerabilities to recover forgotten data and expose its privacy flaws. Extensive experimental results show that FUIA can effectively reveal the private information of forgotten data. To mitigate this privacy leakage, we also explore two potential defense methods, although these come at the cost of reduced unlearning effectiveness and the usability of the unlearned model.

cs.CR↗

arXiv2025

GTree: GPU-Friendly Privacy-preserving Decision Tree Training and Inference

Decision tree (DT) is a widely used machine learning model due to its versatility, speed, and interpretability. However, for privacy-sensitive applications, outsourcing DT training and inference to cloud platforms raise concerns about data privacy. Researchers have developed privacy-preserving approaches for DT training and inference using cryptographic primitives, such as Secure Multi-Party Computation (MPC). While these approaches have shown progress, they still suffer from heavy computation and communication overheads. Few recent works employ Graphical Processing Units (GPU) to improve the performance of MPC-protected deep learning. This raises a natural question: \textit{can MPC-protected DT training and inference be accelerated by GPU?} We present GTree, the first scheme that uses GPU to accelerate MPC-protected secure DT training and inference. GTree is built across 3 parties who securely and jointly perform each step of DT training and inference with GPU. Each MPC protocol in GTree is designed in a GPU-friendly version. The performance evaluation shows that GTree achieves ${\thicksim}11{\times}$ and ${\thicksim}21{\times}$ improvements in training SPECT and Adult datasets, compared to the prior most efficient CPU-based work. For inference, GTree shows its superior efficiency when the DT has less than 10 levels, which is $126\times$ faster than the prior most efficient work when inferring $10^4$ instances with a tree of 7 levels. GTree also achieves a stronger security guarantee than prior solutions, which only leaks the tree depth and size of data samples while prior solutions also leak the tree structure. With \textit{oblivious array access}, the access pattern on GPU is also protected.

cs.CR↗

arXiv2025

ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object

The availability of large-scale remote sensing video data underscores the importance of high-quality interactive segmentation. However, challenges such as small object sizes, ambiguous features, and limited generalization make it difficult for current methods to achieve this goal. In this work, we propose ROS-SAM, a method designed to achieve high-quality interactive segmentation while preserving generalization across diverse remote sensing data. The ROS-SAM is built upon three key innovations: 1) LoRA-based fine-tuning, which enables efficient domain adaptation while maintaining SAM's generalization ability, 2) Enhancement of deep network layers to improve the discriminability of extracted features, thereby reducing misclassifications, and 3) Integration of global context with local boundary details in the mask decoder to generate high-quality segmentation masks. Additionally, we design the data pipeline to ensure the model learns to better handle objects at varying scales during training while focusing on high-quality predictions during inference. Experiments on remote sensing video datasets show that the redesigned data pipeline boosts the IoU by 6%, while ROS-SAM increases the IoU by 13%. Finally, when evaluated on existing remote sensing object tracking datasets, ROS-SAM demonstrates impressive zero-shot capabilities, generating masks that closely resemble manual annotations. These results confirm ROS-SAM as a powerful tool for fine-grained segmentation in remote sensing applications. Code is available at https://github.com/ShanZard/ROS-SAM.

cs.CV↗

arXiv2025

Streamlined Federated Unlearning: Unite as One to Be Highly Efficient

Recently, the enactment of ``right to be forgotten" laws and regulations has imposed new privacy requirements on federated learning (FL). Researchers aim to remove the influence of certain data from the trained model without training from scratch through federated unlearning (FU). While current FU research has shown progress in enhancing unlearning efficiency, it often results in degraded model performance upon achieving the goal of data unlearning, necessitating additional steps to recover the performance of the unlearned model. Moreover, these approaches also suffer from many shortcomings such as high consumption of computational and storage resources. To this end, we propose a streamlined federated unlearning approach (SFU) aimed at effectively removing the influence of the target data while preserving the model performance on the retained data without degradation. We design a practical multi-teacher system that achieves both target data influence removal and model performance preservation by guiding the unlearned model through several distinct teacher models. SFU is both computationally and storage-efficient, highly flexible, and generalizable. We conduct extensive experiments on both image and text benchmark datasets. The results demonstrate that SFU significantly improves time and communication efficiency compared to the benchmark retraining method and significantly outperforms existing SOTA methods. Additionally, we verify the effectiveness of SFU using the backdoor attack.

cs.LG↗

arXiv2025

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

We introduce UniGraspTransformer, a universal Transformer-based network for dexterous robotic grasping that simplifies training while enhancing scalability and performance. Unlike prior methods such as UniDexGrasp++, which require complex, multi-step training pipelines, UniGraspTransformer follows a streamlined process: first, dedicated policy networks are trained for individual objects using reinforcement learning to generate successful grasp trajectories; then, these trajectories are distilled into a single, universal network. Our approach enables UniGraspTransformer to scale effectively, incorporating up to 12 self-attention blocks for handling thousands of objects with diverse poses. Additionally, it generalizes well to both idealized and real-world inputs, evaluated in state-based and vision-based settings. Notably, UniGraspTransformer generates a broader range of grasping poses for objects in various shapes and orientations, resulting in more diverse grasp strategies. Experimental results demonstrate significant improvements over state-of-the-art, UniDexGrasp++, across various object categories, achieving success rate gains of 3.5%, 7.7%, and 10.1% on seen objects, unseen objects within seen categories, and completely unseen objects, respectively, in the vision-based setting. Project page: https://dexhand.github.io/UniGraspTransformer.

cs.RO↗

arXiv2025

NCF: Neural Correspondence Field for Medical Image Registration

Deformable image registration is a fundamental task in medical image processing. Traditional optimization-based methods often struggle with accuracy in dealing with complex deformation. Recently, learning-based methods have achieved good performance on public datasets, but the scarcity of medical image data makes it challenging to build a generalizable model to handle diverse real-world scenarios. To address this, we propose a training-data-free learning-based method, Neural Correspondence Field (NCF), which can learn from just one data pair. Our approach employs a compact neural network to model the correspondence field and optimize model parameters for each individual image pair. Consequently, each pair has a unique set of network weights. Notably, our model is highly efficient, utilizing only 0.06 million parameters. Evaluation results showed that the proposed method achieved superior performance on a public Lung CT dataset and outperformed a traditional method on a head and neck dataset, demonstrating both its effectiveness and efficiency.

eess.IV↗

arXiv2025

Nanometer-resolution 3D Tomographic and Vectorial Near-field Imaging in Dielectric Optical Resonators

All-dielectric optical nano-resonators, exhibiting exotic near-field distributions upon excitations, have emerged as low-loss, versatile and highly adaptable components in nanophotonic structures for manipulating electromagnetic waves and enhancing light-matter interactions. However, achieving experimental full three-dimensional characterization of near-fields within dielectric nano-resonators poses significant challenges. Here, we develop a novel technique using high-order sideband generation to image near-field wave patterns inside dielectric optical nano-resonators. By exploiting the phase-sensitivity of various harmonic orders that enables the detection of near-field distributions at distinct depths, we achieve three-dimensional tomographic and near-field imaging with nanometer resolution inside a micrometer-thick silicon anapole resonator. Furthermore, our method offers high-contrast polarization sensitivity and phase-resolving capability, providing comprehensive vectorial near-field information. Our approach can potentially be applied to diverse dielectric metamaterials, and becomes a valuable tool for comprehensive characterization of near-field wave phenomena within dielectric materials.

physics.optics↗

arXiv2024

Rules and Algorithms for Objective Construction of Fuzzy Sets

This paper aims to present objective methods for constructing new fuzzy sets from known fuzzy or classical sets, defined over the elements of a finite universe's superstructure. The paper proposes rules for assigning membership functions to these new fuzzy sets, leading to two important findings. Firstly, the property concerning the cardinality of a power set in classical theory has been extended to the fuzzy setting, whereby the scalar cardinality of a fuzzy set $\tilde B$ defined on the power set of a finite universe of a fuzzy set $\tilde A$ satisfies $\text{card}(\tilde B)=2^{\text{card}(\tilde A)}$. Secondly, the novel algorithms allow for an arbitrary membership value to be objectively achieved and represented by a specific binary sequence.

math.GM↗

arXiv2024

RepEval: Effective Text Evaluation with LLM Representation

The era of Large Language Models (LLMs) raises new demands for automatic evaluation metrics, which should be adaptable to various application scenarios while maintaining low cost and effectiveness. Traditional metrics for automatic text evaluation are often tailored to specific scenarios, while LLM-based evaluation metrics are costly, requiring fine-tuning or rely heavily on the generation capabilities of LLMs. Besides, previous LLM-based metrics ignore the fact that, within the space of LLM representations, there exist direction vectors that indicate the estimation of text quality. To this end, we introduce RepEval, a metric that leverages the projection of LLM representations for evaluation. Through simple prompt modifications, RepEval can easily transition to various tasks, requiring only minimal sample pairs for direction vector construction. Results on fourteen datasets across two evaluation tasks demonstrate the high effectiveness of our method, which exhibits a higher correlation with human judgments than previous methods, even in complex evaluation scenarios involving pair-wise selection under nuanced aspects. Our work underscores the richness of information regarding text quality embedded within LLM representations, offering insights for the development of new metrics.

cs.CL↗

arXiv2024

DexGrasp-Diffusion: Diffusion-based Unified Functional Grasp Synthesis Method for Multi-Dexterous Robotic Hands

The versatility and adaptability of human grasping catalyze advancing dexterous robotic manipulation. While significant strides have been made in dexterous grasp generation, current research endeavors pivot towards optimizing object manipulation while ensuring functional integrity, emphasizing the synthesis of functional grasps following desired affordance instructions. This paper addresses the challenge of synthesizing functional grasps tailored to diverse dexterous robotic hands by proposing DexGrasp-Diffusion, an end-to-end modularized diffusion-based method. DexGrasp-Diffusion integrates MultiHandDiffuser, a novel unified data-driven diffusion model for multi-dexterous hands grasp estimation, with DexDiscriminator, which employs a Physics Discriminator and a Functional Discriminator with open-vocabulary setting to filter physically plausible functional grasps based on object affordances. The experimental evaluation conducted on the MultiDex dataset provides substantiating evidence supporting the superior performance of MultiHandDiffuser over the baseline model in terms of success rate, grasp diversity, and collision depth. Moreover, we demonstrate the capacity of DexGrasp-Diffusion to reliably generate functional grasps for household objects aligned with specific affordance instructions.

cs.RO↗

arXiv2024

Selective Excitation of Bloch Modes in Canalized Polaritonic Crystals

Polaritonic crystals (PoCs) have experienced significant advancements through involving hyperbolic polaritons in anisotropic materials such as $α$-MoO$_{\rm 3}$, offering a promising approach for nanoscale light control and improved light-matter interactions. Notably, twisted bilayer $α$-MoO$_{\rm 3}$ enables tunable iso-frequency contours (IFCs), especially generating flat IFCs at certain twist angles, which could enhance mode selectivity in their PoCs through the highly collimated and canalized polaritons. This study unveils the selective excitation of Bloch modes in PoCs with square-lattice structures on twisted bilayer $α$-MoO$_{\rm 3}$ with canalized phonon polaritons. Through the optimization of the square lattice design, there is an effective redistribution of canalized polaritons into the reciprocal lattices of PoCs. Fine-tuning the periodicity and orientation of the hole lattice enables momentum matching between flat IFCs and co-linear reciprocal points, allowing precise and directional control over desired Bragg resonances and Bloch modes. This research establishes a versatile platform for tunable polaritonic devices and paves the way for advanced photonic applications.

physics.optics↗