arXiv subjects

Yujun Zhang

Publications and source records attributed to Yujun Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Unveiling Spectral Mechanisms in Training-Free LLM Text Detection

The rapid advancement of Large Language Models (LLMs) makes it increasingly difficult to distinguish human writing from machine-generated text. Training-free detection offers a scalable solution, yet common confidence-based metrics mainly measure average token probabilities and often miss the signal fluctuations that characterize human writing, which we call "generative vitality". Spectral analysis offers a way to capture this vitality, but its mechanism and practical boundaries remain underexplored. In this paper, we analyze spectral detection from both theoretical and empirical perspectives. We connect spectral energy to variance in proxy log-probability trajectories and explain how broader human token choices create the fluctuations used by frequency-domain indicators. We further show that the strength of this signal depends on text length and sampling range: spectral evidence is clearest for long, continuous, constrained generation, while short, fragmented, mixed, and edited settings require complementary confidence and fluctuation views. These findings clarify when frequency-domain detection works and provide guidance for future multi-dimensional detector design.

cs.CL↗

arXiv2026

Group theory of Raman effect in magnetic materials

Despite the wealth of experimental observations on Raman scattering in magnetic materials, the underlying selection rules have remained largely unexplored. In this work, we use Onsager reciprocity relation, other than the conventional corepresentation method, to deal with the mathematical structures of Raman tensors in magnetic groups. Using this approach, we generate Raman tensor tables for all magnetic point groups, and present a comprehensive understanding of the Raman selection rules in magnetic materials with direct product representations method. Our theoretical and numerical results match previous experiments well, and resolve a recent puzzle in the Raman spectroscopy of CrSBr. Moreover, we identify a common but overlooked phenomenon: the magneto-Raman vector can be orthogonal to the magnetic moment direction. Our method and associated Raman tensor tables will be helpful for the Raman studies in both experimental and theoretical domains.

cond-mat.mtrl-sci↗

arXiv2026

Nethira: A Heterogeneity-aware Hierarchical Pre-trained Model for Network Traffic Classification

Network traffic classification is vital for network security and management. The pre-training technology has shown promise by learning general traffic representations from raw byte sequences, thereby reducing reliance on labeled data. However, existing pre-trained models struggle with the gap between traffic heterogeneity (i.e., hierarchical traffic structures) and input homogeneity (i.e., flattened byte sequences). To address this gap, we propose Nethira, a heterogeneity-aware pre-trained model based on hierarchical reconstruction and augmentation. In pre-training, Nethira introduces hierarchical reconstruction at multiple levels-byte, protocol, and packet-capturing comprehensive traffic structural information. During fine-tuning, Nethira proposes a consistency-regularized strategy with hierarchical traffic augmentation to reduce label dependence. Experiments on four public datasets demonstrate that Nethira outperforms seven existing pre-trained models, achieving an average F1-score improvement of 9.11%, and reaching comparable performance with only 1% labeled data on high-heterogeneity network tasks.

cs.NI↗

arXiv2025

OPAL: Operator-Programmed Algorithms for Landscape-Aware Black-Box Optimization

Black-box optimization often relies on evolutionary and swarm algorithms whose performance is highly problem dependent. We view an optimizer as a short program over a small vocabulary of search operators and learn this operator program separately for each problem instance. We instantiate this idea in Operator-Programmed Algorithms (OPAL), a landscape-aware framework for continuous black-box optimization that uses a small design budget with a standard differential evolution baseline to probe the landscape, builds a $k$-nearest neighbor graph over sampled points, and encodes this trajectory with a graph neural network. A meta-learner then maps the resulting representation to a phase-wise schedule of exploration, restart, and local search operators. On the CEC~2017 test suite, a single meta-trained OPAL policy is statistically competitive with state-of-the-art adaptive differential evolution variants and achieves significant improvements over simpler baselines under nonparametric tests. Ablation studies on CEC~2017 justify the choices for the design phase, the trajectory graph, and the operator-program representation, while the meta-components add only modest wall-clock overhead. Overall, the results indicate that operator-programmed, landscape-aware per-instance design is a practical way forward beyond ad hoc metaphor-based algorithms in black-box optimization.

cs.NE↗

arXiv2025

Electrical Modulation and Probing of Antiferromagnetism in Hybrid Multiferroic Heterostructures

The unique features of ultrafast spin dynamics and the absence of macroscopic magnetization in antiferromagnetic (AFM) materials provide a distinct route towards high-speed magnetic storage devices with low energy consumption and high integration density. However, these advantages also introduce challenges in probing and controlling AFM order, thereby restricting their practical applications. In this study, we demonstrate an all-electric control and probing of the AFM order in heavy metal (HM)/AFM insulator (AFMI) heterostructures on a ferroelectric substrate at room temperature (RT). The AFM order was detected by the anomalous Hall effect (AHE) and manipulated by the ferroelectric field effect as well as the piezoelectric effect in heterostructures of Pt/NiO/0.7Pb(Mg$_{1/3}$Nb$_{2/3}$)O$_{3}$--0.3PbTiO$_{3}$ (PMN--PT). The non-volatile control of AFM order gives rise to a 33\% modulation of AHE, which is further evidenced by synchrotron-based X-ray magnetic linear dichroism (XMLD). Combined with the $in$-$situ$ piezoelectric response of AHE, we demonstrate that ferroelectric polarization contributes mainly to the control of the AFM order. Our results are expected to have broader implications for efficient spintronic devices.

cond-mat.mtrl-sci↗

arXiv2025

Nuclear Ptychoscopy: A Ptychographic Framework for Nuclear Spectroscopy

Accessing both amplitude and phase of nuclear response functions is central to fully characterizing light-matter interactions in the X-ray-nuclear regime. Recent work has demonstrated phase retrieval in two-dimensional time- and energy-resolved spectra, establishing the feasibility of phase-sensitive nuclear spectroscopy. Here, we introduce Nuclear Ptychoscopy, a ptychographic framework that adapts algorithms from coherent diffractive imaging to nuclear spectroscopy, enabling reconstruction of the complex response function by exploiting redundancy in two-dimensional spectra. We develop three complementary reconstruction schemes tailored to distinct experimental scenarios: reconstruction with a known analyzer response, blind reconstruction, and reconstruction incorporating partial prior information. In parallel, we develop geometric analysis techniques that elucidate algorithmic behavior and contribute new tools to ptychography. The framework is validated through experimental data and simulations, demonstrating its versatility across diverse nuclear spectroscopy scenarios and bridging nuclear spectroscopy with ptychography. Beyond advancing quantitative nuclear spectroscopy, our framework opens new opportunities for metrology, coherent control, and quantum applications in the X-ray-nuclear regime.

physics.ins-det↗

arXiv2025

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification

Graph Neural Networks (GNNs) have demonstrated strong performance across tasks such as node classification, link prediction, and graph classification, but remain vulnerable to backdoor attacks that implant imperceptible triggers during training to control predictions. While node-level attacks exploit local message passing, graph-level attacks face the harder challenge of manipulating global representations while maintaining stealth. We identify two main sources of anomaly in existing graph classification backdoor methods: structural deviation from rare subgraph triggers and semantic deviation caused by label flipping, both of which make poisoned graphs easily detectable by anomaly detection models. To address this, we propose DPSBA, a clean-label backdoor framework that learns in-distribution triggers via adversarial training guided by anomaly-aware discriminators. DPSBA effectively suppresses both structural and semantic anomalies, achieving high attack success while significantly improving stealth. Extensive experiments on real-world datasets validate that DPSBA achieves a superior balance between effectiveness and detectability compared to state-of-the-art baselines.

cs.LG↗

arXiv2025

Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily

Graph ``pre-training and prompt-tuning'' aligns downstream tasks with pre-trained objectives to enable efficient knowledge transfer under limited supervision. However, current methods typically rely on single-filter backbones (e.g., low-pass), whereas real-world graphs exhibit inherent spectral diversity. Our theoretical \textit{Spectral Specificity} principle reveals that effective knowledge transfer requires alignment between pre-trained spectral filters and the intrinsic spectrum of downstream graphs. This identifies two fundamental limitations: (1) Knowledge Bottleneck: single-filter models suffer from irreversible information loss by suppressing signals from other frequency bands (e.g., high-frequency); (2) Utilization Bottleneck: spectral mismatches between pre-trained filters and downstream spectra lead to significant underutilization of pre-trained knowledge. To bridge this gap, we propose HS-GPPT. We utilize a hybrid spectral backbone to construct an abundant knowledge basis. Crucially, we introduce Spectral-Aligned Prompt Tuning to actively align the downstream graph's spectrum with diverse pre-trained filters, facilitating comprehensive knowledge utilization across both homophily and heterophily. Extensive experiments validate the effectiveness under both transductive and inductive learning settings.

cs.LG↗

arXiv2025

SpecDetect: Simple, Fast, and Training-Free Detection of LLM-Generated Text via Spectral Analysis

The proliferation of high-quality text from Large Language Models (LLMs) demands reliable and efficient detection methods. While existing training-free approaches show promise, they often rely on surface-level statistics and overlook fundamental signal properties of the text generation process. In this work, we reframe detection as a signal processing problem, introducing a novel paradigm that analyzes the sequence of token log-probabilities in the frequency domain. By systematically analyzing the signal's spectral properties using the global Discrete Fourier Transform (DFT) and the local Short-Time Fourier Transform (STFT), we find that human-written text consistently exhibits significantly higher spectral energy. This higher energy reflects the larger-amplitude fluctuations inherent in human writing compared to the suppressed dynamics of LLM-generated text. Based on this key insight, we construct SpecDetect, a detector built on a single, robust feature from the global DFT: DFT total energy. We also propose an enhanced version, SpecDetect++, which incorporates a sampling discrepancy mechanism to further boost robustness. Extensive experiments show that our approach outperforms the state-of-the-art model while running in nearly half the time. Our work introduces a new, efficient, and interpretable pathway for LLM-generated text detection, showing that classical signal processing techniques offer a surprisingly powerful solution to this modern challenge.

cs.CL↗

arXiv2025

Heterogeneity-Oblivious Robust Federated Learning

Federated Learning (FL) remains highly vulnerable to poisoning attacks, especially under real-world hyper-heterogeneity, where clients differ significantly in data distributions, communication capabilities, and model architectures. Such heterogeneity not only undermines the effectiveness of aggregation strategies but also makes attacks more difficult to detect. Furthermore, high-dimensional models expand the attack surface. To address these challenges, we propose Horus, a heterogeneity-oblivious robust FL framework centered on low-rank adaptations (LoRAs). Rather than aggregating full model parameters, Horus inserts LoRAs into empirically stable layers and aggregates only LoRAs to reduce the attack uncover a key empirical observation that the input projection (LoRA-A) is markedly more stable than the output projection (LoRA-B) under heterogeneity and poisoning. Leveraging this, we design a Heterogeneity-Oblivious Poisoning Score using the features from LoRA-A to filter poisoned clients. For the remaining benign clients, we propose projection-aware aggregation mechanism to preserve collaborative signals while suppressing drifts, which reweights client updates by consistency with the global directions. Extensive experiments across diverse datasets, model architectures, and attacks demonstrate that Horus consistently outperforms state-of-the-art baselines in both robustness and accuracy.

cs.LG↗

arXiv2025

Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and further vulnerabilities. These pressures have produced two disjoint research lines: 1) versatile analysis, via network foundation models for low label dependency, and 2) efficient analysis, via hardware offloading for low analysis latency. However, versatility and efficiency have appeared fundamentally incompatible to co-achieve, with prior work consistently sacrificing one for the other, yet we show that this incompatibility is a consequence of polarized design choices across the three components of traffic analysis systems, i.e., traffic processing, model architecture, and analysis execution. In response, we present Nepco, a versatile yet efficient network traffic analysis system that offloads network foundation models to SmartNIC. Our key observation is that discriminative traffic information is concentrated in localized byte regions, motivating versatile yet efficient localized byte-sequence modeling rather than inefficient global modeling. To exploit this without incurring the latency bottlenecks of complex encoding steps, we employ a hardware-friendly processing pipeline that directly embeds raw byte sequences. Crucially, to maintain versatility across diverse tasks, we propose a pattern-aware convolutional architecture equipped with dedicated scoring and gating mechanisms. By exploiting translation invariance, this design dynamically locates and extracts salient semantic signatures. We prototype Nepco on the Nvidia BlueField-3 SmartNIC with multiengine collaborative analysis execution. The experimental results demonstrate that Nepco achieves macro F1 competitive with the best performances achieved by 8 state-of-the-art network foundation models, while reducing end-to-end latency by 328x to the millisecond scale.

cs.NI↗

arXiv2025

Distillation-Enhanced Clustering Acceleration for Encrypted Traffic Classification

Traffic classification plays a significant role in network service management. The advancement of deep learning has established pretrained models as a robust approach for this task. However, contemporary encrypted traffic classification systems face dual limitations. Firstly, pretrained models typically exhibit large-scale architectures, where their extensive parameterization results in slow inference speeds and high computational latency. Secondly, reliance on labeled data for fine-tuning restricts these models to predefined supervised classes, creating a bottleneck when novel traffic types emerge in the evolving Internet landscape. To address these challenges, we propose NetClus, a novel framework integrating pretrained models with distillation-enhanced clustering acceleration. During fine-tuning, NetClus first introduces a cluster-friendly loss to jointly reshape the latent space for both classification and clustering. With the fine-tuned model, it distills the model into a lightweight Feed-Forward Neural Network model to retain semantics. During inference, NetClus performs heuristic merge with near-linear runtime, and valid the cluster purity with newly proposed metrics ASI to identify emergent traffic types while expediting classification. Benchmarked against existing pretrained methods, NetClus achieves up to 6.2x acceleration while maintaining classification degradation below 1%.

cs.NI↗

arXiv2025

Magnetic order dependent photoluminescence from high energy excitons in hBN protected few-layer CrSBr

The detection and manipulation of the spin configurations in layered magnetic semiconductors hold significant interest for developing spintronic devices in two-dimensional limit. In this letter, we report a systematical study on the photoluminescence (PL) from the high energy excitons in few-layer CrSBr and its application on detecting the spin configurations. Besides the broad excitonic emission peak (Xl) at around 1.34 eV, we also observed another strong excitonic emission peak (Xh) at around 1.37 eV in hBN encapsulated 2L sample, which splits into two peaks in 3L and 4L samples. With help of the first principles calculations, we conclude that the Xh peak is associated with the transition between the top valence band and the second lowest conduction band, which is forbidden by the inversion symmetry in 1L CrSBr. Furthermore, the position and intensity of the Xh peak are strongly dependent on the interlayer magnetic order of the CrSBr samples, which provides an efficient way to probe their spin configurations. In addition, when the magnetic field is applied at the easy axis direction, we resolve an intermediate magnetic state besides the antiferromagnetic and ferromagnetic states in 3L and 4L samples. Our results reveal few-layer CrSBr as an ideal platform to study the interaction between the excitons and magnetism.

cond-mat.mes-hall↗

arXiv2025

MamNet: A Novel Hybrid Model for Time-Series Forecasting and Frequency Pattern Analysis in Network Traffic

The abnormal fluctuations in network traffic may indicate potential security threats or system failures. Therefore, efficient network traffic prediction and anomaly detection methods are crucial for network security and traffic management. This paper proposes a novel network traffic prediction and anomaly detection model, MamNet, which integrates time-domain modeling and frequency-domain feature extraction. The model first captures the long-term dependencies of network traffic through the Mamba module (time-domain modeling), and then identifies periodic fluctuations in the traffic using Fourier Transform (frequency-domain feature extraction). In the feature fusion layer, multi-scale information is integrated to enhance the model's ability to detect network traffic anomalies. Experiments conducted on the UNSW-NB15 and CAIDA datasets demonstrate that MamNet outperforms several recent mainstream models in terms of accuracy, recall, and F1-Score. Specifically, it achieves an improvement of approximately 2% to 4% in detection performance for complex traffic patterns and long-term trend detection. The results indicate that MamNet effectively captures anomalies in network traffic across different time scales and is suitable for anomaly detection tasks in network security and traffic management. Future work could further optimize the model structure by incorporating external network event information, thereby improving the model's adaptability and stability in complex network environments.

cs.LG↗

arXiv2025

TraGe: A Generic Packet Representation for Traffic Classification Based on Header-Payload Differences

Traffic classification has a significant impact on maintaining the Quality of Service (QoS) of the network. Since traditional methods heavily rely on feature extraction and large scale labeled data, some recent pre-trained models manage to reduce the dependency by utilizing different pre-training tasks to train generic representations for network packets. However, existing pre-trained models typically adopt pre-training tasks developed for image or text data, which are not tailored to traffic data. As a result, the obtained traffic representations fail to fully reflect the information contained in the traffic, and may even disrupt the protocol information. To address this, we propose TraGe, a novel generic packet representation model for traffic classification. Based on the differences between the header and payload-the two fundamental components of a network packet-we perform differentiated pre-training according to the byte sequence variations (continuous in the header vs. discontinuous in the payload). A dynamic masking strategy is further introduced to prevent overfitting to fixed byte positions. Once the generic packet representation is obtained, TraGe can be finetuned for diverse traffic classification tasks using limited labeled data. Experimental results demonstrate that TraGe significantly outperforms state-of-the-art methods on two traffic classification tasks, with up to a 6.97% performance improvement. Moreover, TraGe exhibits superior robustness under parameter fluctuations and variations in sampling configurations.

cs.NI↗

arXiv2025

NET-SA: An Efficient Secure Aggregation Architecture Based on In-Network Computing

Privacy-preserving machine learning (PPML) enables clients to collaboratively train deep learning models without sharing private datasets, but faces privacy leakage risks due to gradient leakage attacks. Prevailing methods leverage secure aggregation strategies to enhance PPML, where clients leverage masks and secret sharing to further protect gradient data while tolerating participant dropouts. These methods, however, require frequent inter-client communication to negotiate keys and perform secret sharing, leading to substantial communication overhead. To tackle this issue, we propose NET-SA, an efficient secure aggregation architecture for PPML based on in-network computing. NET-SA employs seed homomorphic pseudorandom generators for local gradient masking and utilizes programmable switches for seed aggregation. Accurate and secure gradient aggregation is then performed on the central server based on masked gradients and aggregated seeds. This design effectively reduces communication overhead due to eliminating the communication-intensive phases of seed agreement and secret sharing, with enhanced dropout tolerance due to overcoming the threshold limit of secret sharing. Extensive experiments on server clusters and Intel Tofino programmable switch demonstrate that NET-SA achieves up to 77x and 12x enhancements in runtime and 2x decrease in total client communication cost compared with state-of-the-art methods.

cs.CR↗

arXiv2024

Twisted Convolutional Networks (TCNs): Enhancing Feature Interactions for Non-Spatial Data Classification

Twisted Convolutional Networks (TCNs) are proposed as a novel deep learning architecture for classifying one-dimensional data with arbitrary feature order and minimal spatial relationships. Unlike conventional Convolutional Neural Networks (CNNs) that rely on structured feature sequences, TCNs explicitly combine subsets of input features through theoretically grounded multiplicative and pairwise interaction mechanisms to create enriched representations. This feature combination strategy, formalized through polynomial feature expansions, captures high-order feature interactions that traditional convolutional approaches miss. We provide a comprehensive mathematical framework for TCNs, demonstrating how the twisted convolution operation generalizes standard convolutions while maintaining computational tractability. Through extensive experiments on five benchmark datasets from diverse domains (medical diagnostics, political science, synthetic data, chemometrics, and healthcare), we show that TCNs achieve statistically significant improvements over CNNs, Residual Networks (ResNet), Graph Neural Networks (GNNs), DeepSets, and Support Vector Machine (SVM). The performance gains are validated through statistical testing. TCNs also exhibit superior training stability and generalization capabilities, highlighting their robustness for non-spatial data classification tasks.

cs.CV↗

arXiv2024

Enhance Graph Alignment for Large Language Models

Graph-structured data is prevalent in the real world. Recently, due to the powerful emergent capabilities, Large Language Models (LLMs) have shown promising performance in modeling graphs. The key to effectively applying LLMs on graphs is converting graph data into a format LLMs can comprehend. Graph-to-token approaches are popular in enabling LLMs to process graph information. They transform graphs into sequences of tokens and align them with text tokens through instruction tuning, where self-supervised instruction tuning helps LLMs acquire general knowledge about graphs, and supervised fine-tuning specializes LLMs for the downstream tasks on graphs. Despite their initial success, we find that existing methods have a misalignment between self-supervised tasks and supervised downstream tasks, resulting in negative transfer from self-supervised fine-tuning to downstream tasks. To address these issues, we propose Graph Alignment Large Language Models (GALLM) to benefit from aligned task templates. In the self-supervised tuning stage, we introduce a novel text matching task using templates aligned with downstream tasks. In the task-specific tuning stage, we propose two category prompt methods that learn supervision information from additional explanation with further aligned templates. Experimental evaluations on four datasets demonstrate substantial improvements in supervised learning, multi-dataset generalizability, and particularly in zero-shot capability, highlighting the model's potential as a graph foundation model.

cs.CL↗