检索结果-内蒙古大学图书馆

Hybrid two-level protection system for preserving pre-trained DNN models ownership

Neural Computing and Applications 2024年第34期36卷 21415-21449页

作者： Fkirin, Alaa Moursi, Ahmed Samy Attiya, Gamal El-Sayed, Ayman Shouman, Marwa A. Department of Electrical Engineering Faculty of Engineering Fayoum University Fayoum Egypt Computer Science and Engineering Department Faculty of Electronic Engineering Menoufia Governorate Menouf32952 Egypt

Recent advancements in deep neural networks (DNNs) have made them indispensable for numerous commercial applications. These include healthcare systems and self-driving cars. Training DNN models typically demands substantial time, vast datasets and high computational costs. However, these valuable models face significant risks. Attackers can steal and sell pre-trained DNN models for profit. Unauthorised sharing of these models poses a serious threat. Once sold, they can be easily copied and redistributed. Therefore, a well-built pre-trained DNN model is a valuable asset that requires protection. This paper introduces a robust hybrid two-level protection system for safeguarding the ownership of pre-trained DNN models. The first-level employs zero-bit watermarking. The second-level incorporates an adversarial attack as a watermark by using a perturbation technique to embed the watermark. The robustness of the proposed system is evaluated against seven types of attacks. These are Fast Gradient Method Attack, Auto Projected Gradient Descent Attack, Auto Conjugate Gradient Attack, Basic Iterative Method Attack, Momentum Iterative Method Attack, Square Attack and Auto Attack. The proposed two-level protection system withstands all seven attack types. It maintains accuracy and surpasses current state-of-the-art methods. © The Author(s) 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Modelling and simulation of energy management of power-split hybrid electric vehicles using the discrete EVent system specification

引用

International Journal of Vehicle Systems Modelling and Testing 2024年第1期18卷 33-61页

作者： Maatoug, Abdelfettah Kharoubi, Sahraoui Maaskri, Moustafa Belalem, Ghalem Mahmoudi, Said Faculty of Applied Sciences Science and Technology Department University of Tiaret Tiaret14000 Algeria Faculty of Mathematics and Computer Science Computer Science Department University of Tiaret Tiaret14000 Algeria Faculty of Applied Sciences Electrical Engineering Department University of Tiaret Tiaret14000 Algeria Faculty of Exact and Applied Sciences Computer Science Department University of Oran 1 Ahmed Ben Bella Oran31000 Algeria Faculty of Engineering Computer Science Department University of Mons Mons7000 Belgium

This work provides a basis for studying energy management optimisation in power-split hybrid electric vehicles (PSHEVs) to reduce fuel consumption and increase powertrain efficiency by enforcing a strategy related to battery level and vehicle speed. Three modes were used to operate the vehicle to meet different situations related to available energy and desired speed. These are particularly abundance mode, ascetic mode and optimal mode. For this, a system was designed based on several sub-models written in the discrete EVent system (DEVS) specification. The vehicle's power train and control strategy models were created in the DEVSimPy environment, and a joint simulation was carried out from the composite sub models until the overall model is reached. Simulation results under several driving cycles showed that the proposed system improves the energy consumption of the vehicle in different operating modes of the engines and gives more opportunities to adopt electric motors in vehicle transmission. © 2024 Inderscience Enterprises Ltd.

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

Automated object recognition in high-resolution optical remote sensing imagery

引用

National science Review 2023年第6期10卷 38-41页

作者： Yazhou Yao Tao Chen Hanbo Bi Xinhao Cai Gensheng Pei Guoye Yang Zhiyuan Yan Xian Sun Xing Xu Hai Zhang School of Computer Science and Engineering Nanjing University of Science and Technology Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Key Laboratory of Network Information System Technology (NIST) Aerospace Information Research Institute Chinese Academy of Sciences Department of Computer Science and Technology Tsinghua University School of Computer Science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION With the rapid development of remote sensing technology,high-quality remote sensing images have become widely *** automated object detection and recognition of these images,which aims to automatically locate objects of interest in remote sensing images and distinguish their specific categories,is an important fundamental task in the *** provides an effective means for geospatial object monitoring in many social applications,such as intelligent transportation,urban planning,environmental monitoring and homeland security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network-based image watermarking using discrete wavelet transform

引用

International Journal of Information Technology (Singapore) 2023年第4期15卷 2021-2029页

作者： Tavakoli, Alireza Honjani, Zahra Sajedi, Hedieh Department of Computer Engineering School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Department of Computer Science School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran

With the growing popularity of the Internet, digital images are used and transferred more frequently. Although this phenomenon facilitates easy access to information, it also creates security concerns and violates intellectual property rights by allowing illegal use, copying, and digital content theft. Using watermarks in digital images is one of the most common ways to maintain security. Watermarking is proving and declaring ownership of an image by adding a digital watermark to the original image. Watermarks can be either text or an image placed overtly or covertly in an image and are expected to be challenging to remove. This paper proposes a combination of convolutional neural networks (CNNs) and wavelet transforms to obtain a watermarking network for embedding and extracting watermarks. The network is independent of the host image resolution, can accept all kinds of watermarks, and has only 11 layers while keeping performance. Performance is measured by two terms;the similarity between the extracted watermark and the original one and the similarity between the host image and the watermarked one. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Convolutional neural networks Neural networks Watermarking Wavelet transform

来源：评论

学校读者我要写书评

暂无评论

IBAttack: Being Cautious about Data Labels

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1484-1493页

作者： Agarwal, Akshay Singh, Richa Vatsa, Mayank Ratha, Nalini IISER Bhopal Department of Data Science and Engineering Bhopal462066 India IIT Jodhpur Department of Computer Science and Engineering Rajasthan Jodhpur342037 India University at Buffalo Department of Computer Science and Electrical Engineering BuffaloNY14260 United States

Traditional backdoor attacks insert a trigger patch in the training images and associate the trigger with the targeted class label. Backdoor attacks are one of the rapidly evolving types of attack which can have a significant impact. On the other hand, adversarial perturbations have a significantly different attack mechanism from the traditional backdoor corruptions, where an imperceptible noise is learned to fool the deep learning models. In this research, we amalgamate these two concepts and propose a novel imperceptible backdoor attack, termed as the IBAttack, where the adversarial images are associated with the desired target classes. A significant advantage of the adversarial-based proposed backdoor attack is the imperceptibility as compared to the traditional trigger-based mechanism. The proposed adversarial dynamic attack, in contrast to existing attacks, is agnostic to classifiers and trigger patterns. The extensive evaluation using multiple databases and networks illustrates the effectiveness of the proposed attack. © 2020 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Autoencoder-Based Detection of False Data Injection Attacks Against Data Poisoning in Smart Grids

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1287-1301页

作者： Takiddin, Abdulrahman Ismail, Muhammad Atat, Rachad Davis, Katherine R. Serpedin, Erchin Department of Electrical and Computer Engineering Texas A and M University College StationTX77843 United States Department of Computer Science Tennessee Tech University CookevilleTN38505 United States Department of Electrical and Computer Engineering Program Texas A and M University Qatar Doha23874 Qatar

Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the adopted datasets for training have correct labeling information. However, such an assumption is not always valid as training data might include measurement samples that are incorrectly labeled as benign, namely, adversarial data poisoning samples, which have not been detected before. Neglecting such an aspect makes detectors susceptible to data poisoning. Our investigations revealed that detection rates (DRs) of existing detectors significantly deteriorate by up to 9-29% when subject to data poisoning in generalized and topology-specific settings. Thus, we propose a generalized graph neural network-based anomaly detector that is robust against FDIAs and data poisoning. It requires only benign datasets for training and employs an autoencoder with Chebyshev graph convolutional recurrent layers with attention mechanism to capture the spatial and temporal correlations within measurement data. The proposed convolutional recurrent graph autoencoder model is trained and tested on various topologies (from 14, 39, and 118-bus systems). Due to such factors, it yields stable generalized detection performance that is degraded by only 1.6-3.7% in DR against high levels of data poisoning and unseen FDIAs in unobserved topologies. Impact Statement-Artificial Intelligence (AI) systems are used in smart grids to detect cyberattacks. They can automatically detect malicious actions carried out bymalicious entities that falsifymeasurement data within power grids. Themajority of such systems are data-driven and rely on labeled data for model training and testing. However, datasets are not always correctly labeled since malicious entities might be carrying out cyberattacks without being detected, which leads to training on mislabeled datasets. Such actions might degrade the d

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Optimized ROI Extraction and Pixel Reduction Methods for Kidney Abnormality Detection

Optimized ROI Extraction and Pixel Reduction Methods for Kid...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Hossain, Md Junayed Monir, Md Fahad Ahmed, Tarem Department of Computer Science & Engineering Bangladesh Virginia Polytechnic Institute and State University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798331504847

A global public health concern, Chronic Kidney Disease causes renal failure, cardiovascular disease, and premature death. Given the frequency of kidney diseases and their significant impact on public health, detection of any abnormalities in the kidney is crucial. Effective patient treatment and medical care planning depend on the early and precise diagnosis of a variety of kidney abnormalities. Early detection enable treatments that enhance patient outcomes, slow the progression of disease, and lessen the strain on healthcare systems. In order to detect anomalies in kidney, we utilized the Region of Interest (ROI) and Pixel Reduction techniques separately in this work. We have applied the Bicubic Interpolation method to reduce the size of individual pixels in an image while preserving a significant data of the original image data. A novel hybrid strategy that aims to preserve diagnostic data while reducing computing complexity uses the original images for ROI extraction. The deep learning method is then independently trained and tested using the pixel-reduced and localized dataset. In order to categorize the images, we use Inception V3 and EfficientNet B7 as Deep Learning models. Using the ROI-extracted data, we were able to achieve approximately 99.75% accuracy with the EfficientNet B7 model. Moreover, the same algorithm and dataset were used to obtain 98.45%, 99.02%, and 98.78% Precision, Recall, and F1-score, respectively. This framework provides medical professionals with a helpful prognostic tool to early detect identify various forms of kidney abnormalities. © 2025 IEEE.

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Human Gait Recognition for Biometrics Application Based on Deep Learning Fusion Assisted Framework

引用

computers, Materials & Continua 2024年第1期78卷 357-374页

作者： Ch Avais Hanif Muhammad Ali Mughal Muhammad Attique Khan Nouf Abdullah Almujally Taerang Kim Jae-Hyuk Cha Department of Electrical Engineering HITEC UniversityTaxila47080Pakistan Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Department of Computer Science HITEC UniversityTaxila47080Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Hanyang UniversitySeoul04763Korea

The demand for a non-contact biometric approach for candidate identification has grown over the past ten *** on the most important biometric application,human gait analysis is a significant research topic in computer *** have paid a lot of attention to gait recognition,specifically the identification of people based on their walking patterns,due to its potential to correctly identify people far *** recognition systems have been used in a variety of applications,including security,medical examinations,identity management,and access *** systems require a complex combination of technical,operational,and definitional *** employment of gait recognition techniques and technologies has produced a number of beneficial and well-liked *** proposes a novel deep learning-based framework for human gait classification in video *** framework’smain challenge is improving the accuracy of accuracy gait classification under varying conditions,such as carrying a bag and changing *** proposed method’s first step is selecting two pre-trained deep learningmodels and training fromscratch using deep transfer ***,deepmodels have been trained using static hyperparameters;however,the learning rate is calculated using the particle swarmoptimization(PSO)***,the best features are selected from both trained models using the Harris Hawks controlled Sine-Cosine optimization *** algorithm chooses the best features,combined in a novel correlation-based fusion ***,the fused best features are categorized using medium,bi-layer,and tri-layered neural *** the publicly accessible dataset known as the CASIA-B dataset,the experimental process of the suggested technique was carried out,and an improved accuracy of 94.14% was *** achieved accuracy of the proposed method is improved by the recent state-of-the-art techniques that show the significance of this wor

关键词： Gait recognition covariant factors biometric deep learning fusion feature selection

来源：评论

学校读者我要写书评

暂无评论

Detection of Left Ventricular Cavity from Cardiac MRI Images Using Faster R-CNN

引用

computers, Materials & Continua 2023年第1期74卷 1819-1835页

作者： Zakarya Farea Shaaf Muhammad Mahadi Abdul Jamil Radzi Ambar Ahmed Abdu Alattab Anwar Ali Yahya Yousef Asiri Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn MalaysiaParit RajaBatu Pahat86400JohorMalaysia Department of Computer Science College of Science and ArtsSharurahNajran UniversityNajran61441Saudi Arabia Department of Computer Science Faculty of Computer Science and Info.SystemsThamar UniversityDhamar87246Yemen Department of Computer Science College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia

The automatic localization of the left ventricle(LV)in short-axis magnetic resonance(MR)images is a required step to process cardiac images using convolutional neural networks for the extraction of a region of interest(ROI).The precise extraction of the LV’s ROI from cardiac MRI images is crucial for detecting heart disorders via cardiac segmentation or ***,this task appears to be intricate due to the diversities in the size and shape of the LV and the scattering of surrounding tissues across different ***,this study proposed a region-based convolutional network(Faster R-CNN)for the LV localization from short-axis cardiac MRI images using a region proposal network(RPN)integrated with deep feature classification and *** was trained using images with corresponding bounding boxes(labels)around the LV,and various experiments were applied to select the appropriate layers and set the suitable *** experimental findings showthat the proposed modelwas adequate,with accuracy,precision,recall,and F1 score values of 0.91,0.94,0.95,and 0.95,*** model also allows the cropping of the detected area of LV,which is vital in reducing the computational cost and time during segmentation and classification ***,itwould be an ideal model and clinically applicable for diagnosing cardiac diseases.

关键词： Cardiac short-axis MRI images automatic left ventricle localization deep learning models faster R-CNN

来源：评论

学校读者我要写书评

暂无评论

Comparative Performance of Object Detection Algorithms Under Low Illumination Conditions

Comparative Performance of Object Detection Algorithms Under...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Hossain, Md Junayed Rahman, Shoptorshi Monir, Md Fahad Ahmed, Tarem Department of Computer Science & Engineering Bangladesh Virginia Polytechnic Institute and State University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798331504847

Real-time object detection is pivotal in various computer vision and robotics applications, such as security surveillance, autonomous navigation, and interactive systems. This study evaluates several object detection algorithms under low illumination conditions, comparing traditional methods including SIFT, SURF, ORB, BRISK, KAZE, and AKAZE with the deep learning model YOLOv5. To simulate these conditions, we utilized the COCO dataset and implemented a sequence of preprocessing procedures, such as adjusting the gamma correction throughout the dataset, introducing Gaussian noise, and equalizing the histogram to improve image contrast. Here, YOLOv5 exhibited superior performance, achieving a detection accuracy of 92.47% and a processing time of 45 milliseconds per image. Traditional algorithms like SURF and KAZE, although slower, demonstrated precision rates of 78.54% and 76.86%, respectively. YOLOv5 also identified the highest number of key points and matches. Our findings indicate that while YOLOv5 excels in real-time detection under low-light conditions, traditional methods are effective for specific tasks in resource-constrained environments. This study benchmarks these algorithms and proposes a hybrid approach to enhance real-time object detection systems under low illumination conditions. © 2025 IEEE.

关键词： Deep learning

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：