arXiv subjects

Lei Yu

Publications and source records attributed to Lei Yu.

At least 73 records · Page 4Linked to original sources

arXiv2025

SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection

With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitations: 1) Static analysis methods struggle with complex scenarios. 2) Methods based on specialized pre-trained models perform well on specific datasets but have limited generalization capabilities. In contrast, general-purpose Large Language Models (LLMs) demonstrate impressive ability in adapting to new vulnerability patterns. However, they often underperform on specific vulnerability types compared to methods based on specialized pre-trained models. We also observe that explanations generated by general-purpose LLMs can provide fine-grained code understanding information, contributing to improved detection performance. Inspired by these observations, we propose SAEL, an LLM-based framework for smart contract vulnerability detection. We first design targeted prompts to guide LLMs in identifying vulnerabilities and generating explanations, which serve as prediction features. Next, we apply prompt-tuning on CodeT5 and T5 to process contract code and explanations, enhancing task-specific performance. To combine the strengths of each approach, we introduce an Adaptive Mixture-of-Experts architecture. This dynamically adjusts feature weights via a Gating Network, which selects relevant features using TopK filtering and Softmax normalization, and incorporates a Multi-Head Self-Attention mechanism to enhance cross-feature relationships. This design enables effective integration of LLM predictions, explanation features, and code features through gradient optimization. The loss function jointly considers both independent feature performance and overall weighted predictions. Experiments show that SAEL outperforms existing methods across various vulnerabilities.

cs.CR↗

arXiv2025

DSFormer: A Dual-Scale Cross-Learning Transformer for Visual Place Recognition

Visual Place Recognition (VPR) is crucial for robust mobile robot localization, yet it faces significant challenges in maintaining reliable performance under varying environmental conditions and viewpoints. To address this, we propose a novel framework that integrates Dual-Scale-Former (DSFormer), a Transformer-based cross-learning module, with an innovative block clustering strategy. DSFormer enhances feature representation by enabling bidirectional information transfer between dual-scale features extracted from the final two CNN layers, capturing both semantic richness and spatial details through self-attention for long-range dependencies within each scale and shared cross-attention for cross-scale learning. Complementing this, our block clustering strategy repartitions the widely used San Francisco eXtra Large (SF-XL) training dataset from multiple distinct perspectives, optimizing data organization to further bolster robustness against viewpoint variations. Together, these innovations not only yield a robust global embedding adaptable to environmental changes but also reduce the required training data volume by approximately 30\% compared to previous partitioning methods. Comprehensive experiments demonstrate that our approach achieves state-of-the-art performance across most benchmark datasets, surpassing advanced reranking methods like DELG, Patch-NetVLAD, TransVPR, and R2Former as a global retrieval solution using 512-dim global descriptors, while significantly improving computational efficiency.

cs.CV↗

arXiv2025

SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing

The multi-modal remote sensing foundation model (MM-RSFM) has significantly advanced various Earth observation tasks, such as urban planning, environmental monitoring, and natural disaster management. However, most existing approaches generally require the training of separate backbone networks for each data modality, leading to redundancy and inefficient parameter utilization. Moreover, prevalent pre-training methods typically apply self-supervised learning (SSL) techniques from natural images without adequately accommodating the characteristics of remote sensing (RS) images, such as the complicated semantic distribution within a single RS image. In this work, we present SkySense V2, a unified MM-RSFM that employs a single transformer backbone to handle multiple modalities. This backbone is pre-trained with a novel SSL strategy tailored to the distinct traits of RS data. In particular, SkySense V2 incorporates an innovative adaptive patch merging module and learnable modality prompt tokens to address challenges related to varying resolutions and limited feature diversity across modalities. In additional, we incorporate the mixture of experts (MoE) module to further enhance the performance of the foundation model. SkySense V2 demonstrates impressive generalization abilities through an extensive evaluation involving 16 datasets over 7 tasks, outperforming SkySense by an average of 1.8 points.

cs.CV↗

arXiv2025

On the Adversarial Robustness of Graph Neural Networks with Graph Reduction

As Graph Neural Networks (GNNs) become increasingly popular for learning from large-scale graph data across various domains, their susceptibility to adversarial attacks when using graph reduction techniques for scalability remains underexplored. In this paper, we present an extensive empirical study to investigate the impact of graph reduction techniques, specifically graph coarsening and sparsification, on the robustness of GNNs against adversarial attacks. Through extensive experiments involving multiple datasets and GNN architectures, we examine the effects of four sparsification and six coarsening methods on the poisoning attacks. Our results indicate that, while graph sparsification can mitigate the effectiveness of certain poisoning attacks, such as Mettack, it has limited impact on others, like PGD. Conversely, graph coarsening tends to amplify the adversarial impact, significantly reducing classification accuracy as the reduction ratio decreases. Additionally, we provide a novel analysis of the causes driving these effects and examine how defensive GNN models perform under graph reduction, offering practical insights for designing robust GNNs within graph acceleration systems.

cs.LG↗

arXiv2025

Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on performance metrics such as AUC, accuracy, and TPR@low FPR - either by developing new methods to enhance these metrics or using them to evaluate privacy solutions - we found that it overlooks the disparities among different attacks. These disparities, both between distinct attack methods and between multiple instantiations of the same method, have crucial implications for the reliability and completeness of MIAs as privacy evaluation tools. In this paper, we systematically investigate these disparities through a novel framework based on coverage and stability analysis. Extensive experiments reveal significant disparities in MIAs, their potential causes, and their broader implications for privacy evaluation. To address these challenges, we propose an ensemble framework with three distinct strategies to harness the strengths of state-of-the-art MIAs while accounting for their disparities. This framework not only enables the construction of more powerful attacks but also provides a more robust and comprehensive methodology for privacy evaluation.

cs.LG↗

arXiv2025

Dynamic Bandwidth Allocation for Hybrid Event-RGB Transmission

Event cameras asynchronously capture pixel-level intensity changes with extremely low latency. They are increasingly used in conjunction with RGB cameras for a wide range of vision-related applications. However, a major challenge in these hybrid systems lies in the transmission of the large volume of triggered events and RGB images. To address this, we propose a transmission scheme that retains efficient reconstruction performance of both sources while accomplishing real-time deblurring in parallel. Conventional RGB cameras and event cameras typically capture the same scene in different ways, often resulting in significant redundant information across their outputs. To address this, we develop a joint event and image (E-I) transmission framework to eliminate redundancy and thereby optimize channel bandwidth utilization. Our approach employs Bayesian modeling and the information bottleneck method to disentangle the shared and domain-specific information within the E-I inputs. This disentangled information bottleneck framework ensures both the compactness and informativeness of extracted shared and domain-specific information. Moreover, it adaptively allocates transmission bandwidth based on scene dynamics, i.e., more symbols are allocated to events for dynamic details or to images for static information. Simulation results demonstrate that the proposed scheme not only achieves superior reconstruction quality compared to conventional systems but also delivers enhanced deblurring performance.

cs.CV↗

arXiv2025

Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection

Smart contract vulnerability detection remains a major challenge in blockchain security. Existing vulnerability detection methods face two main issues: (1) Existing datasets lack comprehensive coverage and high-quality explanations for preference learning. (2) Large language models (LLMs) often struggle with accurately interpreting specific concepts in smart contract security. Empirical analysis shows that even after continual pre-training (CPT) and supervised fine-tuning (SFT), LLMs may misinterpret the execution order of state changes, resulting in incorrect explanations despite making correct detection decisions. To address these challenges, we propose Smart-LLaMA-DPO based on LLaMA-3.1-8B. We construct a comprehensive dataset covering four major vulnerability types and machine-unauditable vulnerabilities, including precise labels, explanations, and locations for SFT, as well as high-quality and low-quality output pairs for Direct Preference Optimization (DPO). Second, we perform CPT using large-scale smart contract to enhance the LLM's understanding of specific security practices in smart contracts. Futhermore, we conduct SFT with our comprehensive dataset. Finally, we apply DPO, leveraging human feedback and a specially designed loss function that increases the probability of preferred explanations while reducing the likelihood of non-preferred outputs. We evaluate Smart-LLaMA-DPO on four major vulnerability types: reentrancy, timestamp dependence, integer overflow/underflow, and delegatecall, as well as machine-unauditable vulnerabilities. Our method significantly outperforms state-of-the-art baselines, with average improvements of 10.43% in F1 score and 7.87% in accuracy. Moreover, both LLM evaluation and human evaluation confirm that our method generates more correct, thorough, and clear explanations.

cs.CR↗

arXiv2025

Geometric Signatures of Compositionality Across a Language Model's Lifetime

By virtue of linguistic compositionality, few syntactic rules and a finite lexicon can generate an unbounded number of sentences. That is, language, though seemingly high-dimensional, can be explained using relatively few degrees of freedom. An open question is whether contemporary language models (LMs) reflect the intrinsic simplicity of language that is enabled by compositionality. We take a geometric view of this problem by relating the degree of compositionality in a dataset to the intrinsic dimension (ID) of its representations under an LM, a measure of feature complexity. We find not only that the degree of dataset compositionality is reflected in representations' ID, but that the relationship between compositionality and geometric complexity arises due to learned linguistic features over training. Finally, our analyses reveal a striking contrast between nonlinear and linear dimensionality, showing they respectively encode semantic and superficial aspects of linguistic composition.

cs.CL↗

arXiv2025

QPanda3: A High-Performance Software-Hardware Collaborative Framework for Large-Scale Quantum-Classical Computing Integration

In emerging quantum-classical integration applications, the classical time cost-especially from compilation and protocol-level communication often exceeds the execution time of quantum circuits themselves, posing a severe bottleneck to practical deployment. To overcome these limitations, QPanda3 has been extensively optimized as a high-performance quantum programming framework tailored for the demands of the NISQ era and quantum-classical hybrid workflows. It features optimized circuit compilation, a custom binary instruction stream (OriginBIS), and hardware-aware execution strategies to significantly reduce latency and communication overhead. OriginBIS achieves up to 86.9$\times$ faster encoding and 35.6$\times$ faster decoding than OpenQASM 2.0, addressing critical bottlenecks in hybrid quantum systems. Benchmarks show 10.7$\times$ compilation speedup and up to 597$\times$ acceleration in compiling large-scale circuits (e.g., a 118-qubit W-state) compared to Qiskit. n high-performance simulation, QPanda3 excels in variational quantum algorithms, achieving up to 26$\times$ faster gradient computation than Qiskit, with minimal time-complexity growth across circuit depths. These capabilities make QPanda3 well-suited for scalable quantum algorithm development in finance, materials science, and combinatorial optimization, while supporting industrial deployment and cloud-based execution in quantum-classical hybrid computing scenarios.

cs.PL↗

arXiv2025

Entropic Isoperimetric and Cramér--Rao Inequalities for Rényi--Fisher Information

The de Bruijn identity states that Fisher information is equal to a half of the time-derivative of Shannon differential entropy along heat flow. In the same spirit, a generalized version of Fisher information, which we term the Rényi--Fisher information, is defined as a half of the time-derivative of Rényi differential entropy along heat flow. Based on this Rényi--Fisher information, we establish several sharp Rényi-entropic isoperimetric inequalities, which generalize the classic entropic isoperimetric inequality to the Rényi setting. Utilizing these isoperimetric inequalities, we extend the classical Cramér--Rao inequality from Fisher information to Rényi--Fisher information. We then use these generalized Cramér--Rao inequalities to determine the signs of derivatives of Rényi entropy along heat flow, strengthening existing results on the complete monotonicity of Rényi entropy. We lastly explore the implications of our Rényi-entropic isoperimetric inequalities for entropy power inequalities. We demonstrate that, unlike in the Shannon entropy case, the classic entropy power inequality does not admit a direct extension to Rényi entropy without introducing additional exponents or scaling factors. Furthermore, we establish a sharp Rényi entropy power inequality involving a scaling factor under the assumption that one of two independent random vectors is Gaussian.

cs.IT↗

arXiv2025

Rényi Resolvability, Noise Stability, and Anti-contractivity

This paper investigates three closely related topics -- Rényi resolvability, noise stability, and anti-contractivity. The Rényi resolvability problem refers to approximating a target output distribution of a given channel in the Rényi divergence when the input is set to a function of a given uniform random variable. This problem for the Rényi parameter in $(0,2]\cup\{\infty\}$ was first studied by the present author and Tan in 2019. In the present paper, we provide a complete solution to this problem for the Rényi parameter in the entire range $\mathbb{R}\cup\{\pm\infty\}$. We then connect the Rényi resolvability problem to the noise stability problem, by observing that maximizing or minimizing the $q$-stability of a set is equivalent to a variant of the Rényi resolvability problem. By such a connection, we provide sharp dimension-free bounds on the $q$-stability. We lastly relate the noise stability problem to the anti-contractivity of a Markov operator (i.e., conditional expectation operator), where the terminology ``anti-contractivity'' introduced by us refers to as the opposite property of the well-known contractivity/hyercontractivity. We derive sharp dimension-free anti-contractivity inequalities. All of the results in this paper are evaluated for binary distributions. Our proofs in this paper are mainly based on the method of types, especially strengthened versions of packing-covering lemmas.

cs.IT↗

arXiv2025

Large Deviation Analysis for the Reverse Shannon Theorem

Channel simulation is to simulate a noisy channel using noiseless channels with unlimited shared randomness. This can be interpreted as the reverse problem to Shannon's noisy coding theorem. In contrast to previous works, our approach employs Rényi divergence (with the parameter $α\in(0,\infty)$) to measure the level of approximation. Specifically, we obtain the reverse Shannon theorem under the Rényi divergence, which characterizes the Rényi simulation rate, the minimum communication cost rate required for the Rényi divergence vanishing asymptotically. We also investigate the behaviors of the Rényi divergence when the communication cost rate is above or below the Rényi simulation rate. When the communication cost rate is above the Rényi simulation rate, we provide a complete characterization of the convergence exponent, called the reliability function. When the communication cost rate is below the Rényi simulation rate, we determine the linear increasing rate for the Rényi divergence with parameter $α\in(0,\infty]$, which implies the strong converse exponent for the $α$-order fidelity.

cs.IT↗

arXiv2025

Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting

Recent advances in 3D Gaussian Splatting have shown remarkable potential for novel view synthesis. However, most existing large-scale scene reconstruction methods rely on the divide-and-conquer paradigm, which often leads to the loss of global scene information and requires complex parameter tuning due to scene partitioning and local optimization. To address these limitations, we propose MixGS, a novel holistic optimization framework for large-scale 3D scene reconstruction. MixGS models the entire scene holistically by integrating camera pose and Gaussian attributes into a view-aware representation, which is decoded into fine-detailed Gaussians. Furthermore, a novel mixing operation combines decoded and original Gaussians to jointly preserve global coherence and local fidelity. Extensive experiments on large-scale scenes demonstrate that MixGS achieves state-of-the-art rendering quality and competitive speed, while significantly reducing computational requirements, enabling large-scale scene reconstruction training on a single 24GB VRAM GPU. The code will be released at https://github.com/azhuantou/MixGS.

cs.CV↗

arXiv2025

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To address this issue, recent research has introduced Retrieval-Augmented Generation (RAG) techniques, commonly used in Large Language Models (LLM), into VLM, incorporating external multi-modal knowledge to enhance the accuracy and practicality of VLM systems. Nevertheless, the RAG in LLM may be susceptible to data poisoning attacks. RAG-based VLM may also face the threat of this attack. This paper first reveals the vulnerabilities of the RAG-based large model under poisoning attack, showing that existing single-modal RAG poisoning attacks have a 100\% failure rate in multi-modal RAG scenarios. To address this gap, we propose Spa-VLM (Stealthy Poisoning Attack on RAG-based VLM), a new paradigm for poisoning attacks on large models. We carefully craft malicious multi-modal knowledge entries, including adversarial images and misleading text, which are then injected into the RAG's knowledge base. When users access the VLM service, the system may generate misleading outputs. We evaluate Spa-VLM on two Wikipedia datasets and across two different RAGs. Results demonstrate that our method achieves highly stealthy poisoning, with the attack success rate exceeding 0.8 after injecting just 5 malicious entries into knowledge bases with 100K and 2M entries, outperforming state-of-the-art poisoning attacks designed for RAG-based LLMs. Additionally, we evaluated several defense mechanisms, all of which ultimately proved ineffective against Spa-VLM, underscoring the effectiveness and robustness of our attack.

cs.CR↗

arXiv2025

An Unsupervised Learning Method for Radio Interferometry Deconvolution

Given the incomplete sampling of spatial frequencies by radio interferometers, achieving precise restoration of astrophysical information remains challenging. To address this ill-posed problem, compressive sensing(CS) provides a robust framework for stable and unique recovery of sky brightness distributions in noisy environments, contingent upon satisfying specific conditions. We explore the applicability of CS theory and find that for radio interferometric telescopes, the conditions can be simplified to sparse representation. {Building on this insight, we develop a deep dictionary (realized through a convolutional neural network), which is designed to be multi-resolution and overcomplete, to achieve sparse representation and integrate it within the CS framework. The resulting method is a novel, fully interpretable unsupervised learning approach that combines} the mathematical rigor of CS with the expressive power of deep neural networks, effectively bridging the gap between deep learning and classical dictionary methods. {During the deconvolution process, the model image and the deep dictionary are updated alternatively.} This approach enables efficient and accurate recovery of extended sources with complex morphologies from noisy measurements. Comparative analyses with state-of-the-art algorithms demonstrate the outstanding performance of our method, i.e., achieving a dynamic range (DR) nearly 45 to 100 times higher than that of multiscale CLEAN (MS-CLEAN).

astro-ph.IM↗

arXiv2025

Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space

We establish a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness under the squared error distortion measure and the squared Wasserstein-2 perception measure. Moreover, it is shown that this single-letter characterization can be explicitly evaluated for the Gaussian source. Various notions of universal representation are also clarified.

cs.IT↗

arXiv2025

Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations

LLMs often adopt an assertive language style also when making false claims. Such ``overconfident hallucinations'' mislead users and erode trust. Achieving the ability to express in language the actual degree of uncertainty around a claim is therefore of great importance. We find that ``verbal uncertainty'' is governed by a single linear feature in the representation space of LLMs, and show that this has only moderate correlation with the actual ``semantic uncertainty'' of the model. We apply this insight and show that (1) the mismatch between semantic and verbal uncertainty is a better predictor of hallucinations than semantic uncertainty alone and (2) we can intervene on verbal uncertainty at inference time and reduce confident hallucinations on short-form answers, achieving an average relative reduction of ~30%.

cs.CL↗

arXiv2025

Designing optimal subsidy schemes and recycling plans for sustainable treatment of construction and demolition waste

More than 10 billion tons of construction and demolition waste (CW) are generated globally each year, exerting a significant impact on the environment. In the CW recycling process, the government and the carrier are the two primary stakeholders. The carrier is responsible for transporting CW from production sites to backfill sites or processing facilities, with a primary focus on transport efficiency and revenue. Meanwhile, the government aims to minimize pollution from the recycling system, which is influenced by transport modes, shipment distances, and the processing methods used for CW. This paper develops a bi-objective, bi-level optimization model to address these challenges. The upper-level model is a linear programming model that optimizes the government's subsidy scheme, while the lower-level model is a minimum-cost flow model that optimizes the carrier's recycling plan. A hybrid heuristic solution method is proposed to tackle the problem's complexity. A case study in Chengdu, China, demonstrates the computational efficiency of the model and its small solution gap. With an optimized subsidy scheme and recycling plan, pollution can be reduced by over 29.29% through a relatively small investment in subsidies.

math.OC↗