检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural network-driven parallel accelerated selective image encryption with semantic understanding

引用

The European Physical Journal Special Topics 2025年 1-16页

作者： Song, Wei Fu, Chong Zheng, Yu Chen, Junxin Zhang, Yanfeng School of Computer Science and Engineering Northeastern University Shenyang China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China University of California Irvine Irvine USA School of Software Dalian University of Technology Dalian China

Existing batch image encryption schemes often directly encrypt images without considering their source. However, in real-life scenarios, these images are typically part of a larger collection stored in a directory on a computer or in the cloud. To efficiently protect those sensitive images distributed within the collection, we rethink selective image encryption (SIE) from the perspective of batch image encryption and proposes a novel SIE scheme using deep neural networks (DNN) and parallel computing. First, a DNN method is employed to identify sensitive images by analyzing their semantics. Next, a parallel cross-bitplane permutation algorithm is introduced to shuffle the retrieved images in bit-level. Then, a bi-directional diffusion strategy is employed to spread the encryption influence of a pixel to all images. Experimental results demonstrate the proposed scheme effectively understands the semantic of images, identifies sensitive images, and encrypts them with high permutation and diffusion efficiency. Further security analyses show that the proposed algorithm successfully resists various attacks with desired performance, including achieving high information entropy and low correlation coefficients in statistical analysis, and ideal values of the number of pixels changing rate (NPCR) and the unified averaged changing intensity (UACI) to resist differential attack, as well as high key sensitivity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An intelligent cylindrical reflector for airborne virus detection 20

An intelligent cylindrical reflector for airborne virus dete...

引用

20th International Multi-Conference on systems, Signals and Devices, SSD 2023

作者： Hadded, Ahmed Ayed, Mossaad Ben Alshaya, Shaya A. Sfax University Computer and Embedded System Laboratory National Engineering School of Sfax Sfax3038 Tunisia Sousse University Electronic Industrial ENISo Tunisia Sfax University Tunisia Computer and Embedded System Laboratory ENIS Sfax3038 Tunisia Majmaah University Digital Transformation and E-Transactions Faculty of Sciences and Humanities Sciences Prince Sultan University Department of Computer Science Majmaah11952 Saudi Arabia

ISBN: (纸本)9798350332568

In 2020, the world suffered from the COVID-19 pandemic. This situation highlighted the considerable need for systems to detect viruses quickly. Providing an accurate e-health system that detects, monitors, and controls virus spread became necessary. Countries attempt to reduce the virus's spread using basic processes such as quarantine and lockdown. Early virus detection is requested to reduce the threat and decrease the propagation of the pandemic. This paper proposes an attempt to avoid speed-up spreading based on airborne virus detection. The suggested detection based on the SiNW-FET biosensor is not approved as a standardized diagnostic test. To support the airborne detection methodology, a metasurface technology based on Reflector cylindrical antenna with a sensing unit is proposed to detect viruses. The proposal considered the propagation delays and concentration of a virus. Conducted results prove that the receiver's volume is considered a primary key to an accurate detection rather than the virus's concentration. © 2023 IEEE.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection Based on Pre-trained Code Language Model and Convolutional Neural Network 36

Vulnerability Detection Based on Pre-trained Code Language M...

引用

36th International Conference on Software engineering and Knowledge engineering, SEKE 2024

作者： Liao, Tingfeng Lu, Lu Liang, Zhihong Suo, Siliang School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Pengcheng Laboratory Shenzhen China Electric Power Research Institute CSG Guangzhou China Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China

ISBN: (纸本)1891706594

Software vulnerabilities damage the reliability of software systems. Recently, many methods based on deep learning have been proposed for vulnerability detection by learning features from code sequences or various property graphs. However, sequence-based methods frequently fail to consider the structural information of the code, whereas graph-based methods often encounter difficulties in capturing long-distance contextual semantic information. To overcome these limitations, we propose PTCN, a novel vulnerability detection method that integrates Pre-Trained code language model and Convolutional Neural Network (CNN). First, the code tokens sequence and the propagation chains are constructed from the source code in preparation for the subsequent feature extraction. Next, GraphCodeBERT, a graph-based pre-trained code language model, is introduced as a means of learning both the semantic and structural information contained in the code tokens sequence and the propagation chains. Then, a CNN architecture is designed to effectively extract the crucial vulnerability features from the hidden states of the last Transformer layer of GraphCodeBERT for vulnerability detection. The experiments on the public benchmark dataset REVEAL indicate that PTCN outperforms the state-of-the-art methods with respect to the Accuracy and F1-score metrics by 3.41%-15.80% and 22.68%-104.27%, respectively. © 2024 Knowledge systems Institute Graduate school. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature 39

Breaking Barriers in Physical-World Adversarial Examples: Im...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China

ISBN: (纸本)157735897X

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method's superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method's effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Graphene-based dual-function acoustic transducers for machine learning-assisted human-robot interfaces

引用

InfoMat 2023年第2期5卷 66-79页

作者： Hao Sun Xin Gao Liang-Yan Guo Lu-Qi Tao Zi Hao Guo Yangshi Shao Tianrui Cui Yi Yang Xiong Pu Tian-Ling Ren Institute of Microelectronics and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijingPeople's Republic of China CAS Center for Excellence in Nanoscience Beijing Key Laboratory of Micro-nano Energy and SensorBeijing Institute of Nanoenergy and NanosystemsChinese Academy of SciencesBeijingPeople's Republic of China State Key Laboratory of Power Transmission Equipment and System Security and New Technology School of Electrical EngineeringChongqing UniversityChongqingPeople's Republic of China School of Computer Science&Technology Beijing Institute of TechnologyBeijingPeople's Republic of China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijingPeople's Republic of China

Human–robot interface(HRI)electronics are critical for realizing robotic ***,we report graphene-based dual-function acoustic transducers for machine learning-assisted human–robot interfaces(GHRI).The GHRI functions both an artificial ear through the triboelectric acoustic sensing mechanism and an artificial mouth through the thermoacoustic sound emission *** success of the integrated device is also attributed to the multifunctional laser-induced graphene,as either triboelectric materials,electrodes,or thermoacoustic *** systematically optimizing the structure parameters,the GHRI achieves high sensitivity(4500 mV Pa^(–1))and operating durability(1000000 cycles and 60 days),capable of recognizing speech identities,emotions,content,and other information in the human *** the assistance of machine learning,30 speech categories are trained by a convolutional neural network,and the accuracy reaches 99.66%and 96.63%in training datasets and test ***,GHRI is used for artificial intelligence communication based on recognized speech *** work shows broad prospects for the development of robotic intelligence.

关键词： human-robot interface laser-induced graphene machine learning thermoacoustic triboelectric nanogenerator

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining 23

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China and Zhejiang-HUST Joint Research Center for Graph Processing Zhejiang Lab China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798350323481

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Condition Monitoring of Low Voltage Motors in Harsh Environments with Ladybug Beetle Optimization and Context-Aware Graph Convolutional Networks 4

Enhanced Condition Monitoring of Low Voltage Motors in Harsh...

引用

4th International Conference on Sustainable Expert systems, ICSES 2024

作者： Rajasekar, P. Tiwari, Praveen Prakash Sharmila, L. Garg, Akriti Srinivas, Rayudu Tallapragada, V. V. Satyanarayana Srm Institute of Science and Technology Department of Data Science and Business System Tamil Nadu Kattankulathur603203 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai600062 India Mahatma Jyotiba Phule Rohilkhand University Department of Electrical Engineering Uttar Pradesh Bareilly243006 India Aditya College of Engineering & Technology Department of Electrical and Electronics Engineering Andhra Pradesh Surampalem533437 India School of Engineering Mohan Babu University Department of Electronics and Communication Engineering Andhra Pradesh Tirupati517102 India

ISBN: (纸本)9798331540364

Low voltage motors are essential in many applications in contemporary industrial settings, as they power machines and guarantee efficient operations. However, these motors often operate in harsh environments where they are exposed to factors such as extreme temperatures, moisture, dust, and vibrations, which can lead to premature wear and failure. This paper proposes a hybrid method for low voltage motor condition monitoring in challenging industrial environments. The proposed method is the combined execution of Ladybug Beetle Optimization algorithm (LBOA) and Heterogeneous Context-Aware Graph Convolutional Network (HCAGCN). Hence it is named as LBOA-HCAGCN technique. Initially, the input data is collected from Triboelectric vibration sensors. Then, the collected data is fed into preprocessing utilizing Generalized Multi-kernel Maximum Correntropy Kalman Filter (GMKMCKF). This filter normalizes and cleans the data by effectively removing noise. Recursive Hilbert Transform (RHT) is used to extract time domain features such as mean, Root Mean Square (RMS), Peak-to-Peak Value, Skewness, and Kurtosis. Then the extracted features are given to HCAGCN for classify the motor health conditions such as normal, broken-bar, bowed-bar, bowed-rotor, faulty bearing, and voltage imbalance. In general, HCAGCN does not express adapting optimization strategies to determine optimal parameters to classify motor conditions. Hence, the LBOA is used to optimize the weight parameter of the HCAGCN which accurately classify motor conditions. The proposed LBOA-HCAGCN is implemented in MATLAB. Performance indicators such as Mean Absolute Error (MAE), Precision, and Accuracy were used to analyze the effectiveness of the proposed approach. Comparing the proposed LBOA-HCAGCN methodology to other existing techniques like Deep Residual Neural Network (DRNN), Convolutional Neural Network (CNN), and Recursive Neural Network (RNN), it achieves 25.8%, 26.4%, and 24.7% greater accuracy, 26.7%, 29.4%, and

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs 25

UICopilot: Automating UI Synthesis via Hierarchical Code Gen...

引用

34th ACM Web Conference, WWW 2025

作者： Gui, Yi Wan, Yao Li, Zhen Zhang, Zhongyi Chen, Dongping Zhang, Hongyu Su, Yi Chen, Bohua Zhou, Xing Jiang, Wenbin Zhang, Xiangliang Huazhong University of Science and Technology Wuhan China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster Grid Computing Lab School of Computer Science and Technology China

ISBN: (纸本)9798400712746

Automating the synthesis of User Interfaces (UIs) plays a crucial role in enhancing productivity and accelerating the development lifecycle, reducing both development time and manual effort. Recently, the rapid development of Multimodal Large Language Models (MLLMs) has made it possible to generate front-end Hypertext Markup Language (HTML) code directly from webpage designs. However, real-world webpages encompass not only a diverse array of HTML tags but also complex stylesheets, resulting in significantly lengthy code. The lengthy code poses challenges for the performance and efficiency of MLLMs, especially in capturing the structural information of UI designs. To address these challenges, this paper proposes UICopilot, a novel approach to automating UI synthesis via hierarchical code generation from webpage designs. The core idea of UICopilot is to decompose the generation process into two stages: first, generating the coarse-grained HTML hierarchical structure, followed by the generation of fine-grained code. To validate the effectiveness of UICopilot, we conduct experiments on a real-world dataset, i.e., WebCode2M. Experimental results demonstrate that UICopilot significantly outperforms existing baselines in both automatic evaluation metrics and human evaluations. Specifically, statistical analysis reveals that the majority of human annotators prefer the webpages generated by UICopilot over those produced by GPT-4V. © 2025 Copyright held by the owner/author(s).

关键词： Web Design

来源：评论

学校读者我要写书评

暂无评论

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：