检索结果-内蒙古大学图书馆

Robust Watermarking Based on Multi-layer Watermark Feature Fusion

IEEE Transactions on Multimedia 2025年

作者： Wu, Shaowu Lu, Wei Luo, Xiangyang Sun Yat-Sen University School of Computer Science and Engineering Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China State Key Laboratory of Mathematical Engineering and Advanced Computing Henan450002 China

The purpose of robust image watermarking is to embed a watermark into a carrier image in an invisible form and extract the watermark successfully even under noise interference conditions to achieve copyright confirmation and traceability. Although watermarking methods based on deep learning can improve the robustness by adding a noise simulation layer, few theoretical analyses of the codec structure have been conducted. Theoretical explainability is the theoretical basis for developing a network architecture, which plays a guiding role in network development. On the basis of the interpretability of convolutional networks, this paper analyzes the mathematical process of embedding and extracting watermarks in codecs and proposes a novel watermarking framework based on multi-layer watermark feature fusion. Specifically, the encoder can be a convolutional network structure of arbitrary depth, whereas the decoder needs only to adopt its corresponding deconvolution structure. To improve the quality and robustness of the generated watermarked image, the watermark is associated with an arbitrary layer feature space in the decoder. In the decoder, the network quickly converges to each original encoding feature space through the deconvolution structure, thus decoupling the watermark features. Finally, the watermark is extracted via the automatic fusion of multi-layer watermark features. The experimental results show that the proposed method is suitable for few-shot learning, and its invisibility, robustness and generalization performance on multiple datasets are significantly better than those of other advanced methods. © 2025 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Pixel+ and Pixel++: compact and efficient forward-secure multi-signatures for PoS blockchain consensus 24

Pixel+ and Pixel++: compact and efficient forward-secure mul...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Jianghong Wei Guohua Tian Ding Wang Fuchun Guo Willy Susilo Xiaofeng Chen State Key Laboratory of Integrated Service Networks (ISN) Xidian University and State Key Laboratory of Mathematical Engineering and Advanced Computing State Key Laboratory of Integrated Service Networks (ISN) Xidian University College of Cyber Science Nankai University School of Computing and Information Technology University of Wollongong

ISBN: (纸本)9781939133441

Multi-signature schemes have attracted considerable attention in recent years due to their popular applications in PoS blockchains. However, the use of general multi-signature schemes poses a critical threat to the security of PoS blockchains once signing keys get corrupted. That is, after an adversary obtains enough signing keys, it can break the immutable nature of PoS blockchains by forking the chain and modifying the history from some point in the past. Forward-secure multi-signature (FS-MS) schemes can overcome this issue by periodically updating signing keys. The only FS-MS construction currently available is Drijvers et al's Pixel, which builds on pairing groups and only achieves forward security at the time period *** this work, we present new FS-MS constructions that either are free from pairing or capture forward security at the individual message level (i.e., fine-grained forward security). Our first construction Pixel+ works for a maximum number of time periods T. Pixel+ signatures consist of only one group element, and can be verified using two exponentiations. It is the first FS-MS from RSA assumption, and has 3.5x and 22.8x faster signing and verification than Pixel, respectively. Our second FS-MS construction Pixel++ is a pairing-based one. It immediately revokes the signing key's capacity of re-signing the message after creating a signature on this message, rather than at the end of the current time period. Thus, it provides more practical forward security than Pixel. On the other hand, Pixel++ is almost as efficient as Pixel in terms of signing and verification. Both Pixel+ and Pixel++ allow for non-interactive aggregation of signatures from independent signers and are proven to be secure in the random oracle model. In addition, they also support the aggregation of public keys, significantly reducing the storage overhead on PoS *** demonstrate how to integrate Pixel+ and Pixel++ into PoS blockchains. As a proof-of-concept, we provid

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

Science China(Information Sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

Obtaining Electromagnetic Properties of Multi-Type Media in Realistic Environments:state-of-the-Art and Prospects

引用

China Communications 2025年第1期22卷 25-40页

作者： Guo Lantu Guan Ke Liu Ting He Danping Zhang Haixia Zhu Qiuming Lu Jun Zhang Minggao China Research Institute of Radiowave Propagation Qingdao 266107China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong UniversityBeijing 100044China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Control Science and Engineering Shandong UniversityJinan 250061China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Jinan 250061China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China Jiaxing University Jiaxing 314001China

To meet the requirements of electromagnetic(EM)theory and applied physics,this study presents an overview of the state-of-the-art research on obtaining the EM properties of media and points out potential solutions that can break through the bottlenecks of current ***,based on the survey of three mainstream approaches for acquiring EM properties of media,we identify the difficulties when implementing them in realistic *** a focus on addressing these problems and challenges,we propose a novel paradigm for obtaining the EM properties of multi-type media in realistic ***,within this paradigm,we describe the implementation approach of the key technology,namely“multipath extraction using heterogeneous wave propagation data in multi-spectrum cases”.Finally,the latest measurement and simulation results show that the EM properties of multi-type media in realistic environments can be precisely and efficiently acquired by the methodology proposed in this study.

关键词： electromagnetic properties of media multi-type media parameter inversion ray tracing realistic environment

来源：评论

学校读者我要写书评

暂无评论

Triangle Matters! TopDyG: Topology-aware Transformer for Link Prediction on Dynamic Graphs 25

Triangle Matters! TopDyG: Topology-aware Transformer for Lin...

引用

Proceedings of the ACM on Web Conference 2025

作者： Xin Zhang Fei Cai Jianming Zheng Zhiqiang Pan Wanyu Chen Honghui Chen Chonghao Chen National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China College of Electronic Countermeasures National University of Defense Technology Hefei China

ISBN: (纸本)9798400712746

Dynamic graph link prediction is widely utilized in the complex web of the real world, such as social networks, citation networks, recommendation systems, etc. Recent Transformer-based link prediction methods on dynamic graphs not only fail to model the fine-grained structures such as triangles with the vanilla Transformers in the graph serialization process, but also amplify the imbalanced distribution of graphs because of their over-estimation of high-degree nodes. To tackle these issues, we propose a Topology-aware Transformer on Dynamic Graph (TopDyG) for link prediction, consisting of a topology injected Transformer (Ti-Transformer) and a mutual information learning (Mi-Learning). The Ti-Transformer explores the explicit structure of serialized graphs, capturing the topological features. The Mi-Learning mines the relationship between nodes by modeling the mutual information with a prior knowledge, alleviating the over-estimation of high-degree nodes when applying the Transformer-based models for the dynamic graph link prediction task. Extensive experiments on four public datasets containing both transductive and inductive settings present the superiority of our proposal. In particular, TopDyG presents an improvement of 43.27% and 28.75% against the state-of-the-art baselines in terms of NDCG and Jaccard, respectively. The advantages are especially obvious on the high-density graphs.

关键词： dynamic graphs

来源：评论

学校读者我要写书评

暂无评论

FASTEN: Video Event Localization based on Audio-Visual Feature Alignment and Multi-Scale Temporal Enhancement

引用

IEEE Signal Processing Letters 2025年 32卷 2010-2014页

作者： Liu, Yin Wu, Qin Zeng, Mingyong Liu, Yahan Pan, Yuying Jiangnan University School of Artificial Intelligence and Computer Science Wuxi 214122 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214083 China Jiangnan University School of Internet of Things Engineering Wuxi 214122 China

The audio-visual event localization task investigates how audio and visual modalities can mutually enhance video event localization. Current methods often rely on single-modality features or lack effective initial alignment between modalities. Although feature pyramids with multiple resolutions are commonly used, the effective and efficient mining of cross-modal and cross-level semantics remains a challenge. In this letter, we propose FASTEN, which stands for audio-visual Feature Alignment and multi-Scale Temporal ENhancement. Novel features derived from an initially aligned multimodal model are introduced and have been shown to be remarkably beneficial. We design an efficient encoder by sharing weights across all pyramid levels and propose a weighted cross-modal attention module to facilitate interaction between modalities. Additionally, global and local pyramids are fused to jointly capture multi-scale temporal dependencies. Evaluated on UnAV-100 and AVE, our method significantly outperforms competing solutions while reducing parameters and computational FLOPs greatly. © 1994-2012 IEEE.

关键词： Audio-visual event localization cross-modal fusion multi-scale enhancement

来源：评论

学校读者我要写书评

暂无评论

Minimizing transformer inference overhead using controlling element on Shenwei AI accelerator

引用

Frontiers of Information Technology & Electronic engineering 2025年第4期26卷 605-622页

作者： Zhao, Yulong Wu, Chunzhi Wang, Yizhuo Zhang, Lufei Zhang, Yaguang Shen, Wenyuan Fan, Hao Fang, Hankang Qin, Yi Liu, Xin State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China School of Non-Commissioned Officer Space Engineering University Beijing China National Supercomputing Center in Wuxi Wuxi China Zhejiang Lab Hangzhou China National Research Centre of Parallel Computer Engineering and Technology Beijing China

Transformer models have become a cornerstone of various natural language processing (NLP) tasks. However, the substantial computational overhead during the inference remains a significant challenge, limiting their deployment in practical applications. In this study, we address this challenge by minimizing the inference overhead in transformer models using the controlling element on artificial intelligence (AI) accelerators. Our work is anchored by four key contributions. First, we conduct a comprehensive analysis of the overhead composition within the transformer inference process, identifying the primary bottlenecks. Second, we leverage the management processing element (MPE) of the Shenwei AI (SWAI) accelerator, implementing a three-tier scheduling framework that significantly reduces the number of host-device launches to approximately 1/10 000 of the original PyTorch-GPU setup. Third, we introduce a zero-copy memory management technique using segment-page fusion, which significantly reduces memory access latency and improves overall inference efficiency. Finally, we develop a fast model loading method that eliminates redundant computations during model verification and initialization, reducing the total loading time for large models from 22 128.31 ms to 1041.72 ms. Our contributions significantly enhance the optimization of transformer models, enabling more efficient and expedited inference processes on AI accelerators.

关键词： Fast model loading Three-tier scheduling TP181 Transformer inference optimization Zero-copy memory management

来源：评论

学校读者我要写书评

暂无评论

A Note on "Constructing Bent Functions Outside the Maiorana-McFarland Class Using a General Form of Rothaus"

arXiv

引用

arXiv 2025年

作者： Guo, Fei Wang, Zilong Gong, Guang State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Zhengzhou450001 China State Key Laboratory of Integrated Service Networks Xidian University Xi’an710071 China Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

In 2017, Zhang et al. proposed a question (not open problem) and two open problems in [IEEE TIT 63 (8): 5336–5349, 2017] about constructing bent functions by using Rothaus’ construction. In this note, we prove that the sufficient conditions of Rothaus’ construction are also necessary, which answers their question. Besides, we demonstrate that the second open problem, which considers the iterative method of constructing bent functions by using Rothaus’ construction, has only a trivial solution. It indicates that all bent functions obtained by using Rothaus’ construction iteratively can be generated from the direct sum of an initial bent function and a quadratic bent function. This directly means that Zhang et al.’s construction idea makes no contribution to the construction of bent functions. To compensate the weakness of their work, we propose an iterative construction of bent functions by using a secondary construction in [DCC 88: 2007–2035, 2020]. © 2025, CC BY-NC-ND.

关键词： Hadamard transforms

来源：评论

学校读者我要写书评

暂无评论

On greedy randomized coordinate updating iteration methods for solving symmetric eigenvalue problems

引用

Applied Numerical Mathematics 2025年 216卷 76-97页

作者： Zhong-Zhi Bai State Key Laboratory of Mathematical Sciences Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 PR China State Key Laboratory of Scientific/Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences P.O. Box 2719 Beijing 100190 PR China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 PR China

In order to compute the smallest eigenvalue and its corresponding eigenvector of a large-scale, real, and symmetric matrix, we propose a class of greedy randomized coordinate updating iteration methods based on the principle that the indices of larger entries in absolute value of the current residual are selected with a higher probability and, with respect to this index set, the next iterate is updated from the current iterate along with the selected coordinate such that the corresponding entry of the residual is annihilated, resulting in fast convergence rates of the proposed iteration methods. Under appropriate conditions, we prove the convergence of both sequences of the Rayleigh-quotients and the acute angles between the iterates and the eigenvector in terms of the expectation. By numerical experiments, we show that this class of greedy randomized coordinate updating iteration methods are advantageous over the parameterized power method and the coordinate descent method in both iteration counts and computing times. Moreover, with theoretical analysis and computational performance, we confirm that the convergence property of this class of iteration methods can be improved significantly by suitably choosing the arbitrary nonnegative parameter involved in the greedy probability criterion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Admissibly Randomized Coordinate Descent Methods for computing Extreme Eigenpairs of Symmetric Matrices

引用

Numerical Linear Algebra with Applications 2025年第2期32卷

作者： Bai, Zhong-Zhi Chen, Yan-Qi State Key Laboratory of Mathematical Sciences State Key Laboratory of Scientific/Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China

For solving symmetric eigenvalue problems of extremely large matrices that cannot be stored in a whole in the computer memory, we propose a class of admissibly randomized coordinate descent methods by minimizing the corresponding Rayleigh quotients. These iteration methods only call of and operate on a column of the matrix at each of their iteration steps, so they require a small computer memory and have a small computational complexity. We analyze the convergence property of these admissibly randomized coordinate descent methods and confirm their implemental effectiveness by numerical experiments. © 2025 John Wiley & Sons Ltd.

关键词： convergence property coordinate descent method randomized iteration symmetric eigenvalue problem

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：