检索结果-内蒙古大学图书馆

The Security of Using Large Language Models:A Survey With Emphasis on ChatGPT

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 1-26页

作者： Wei Zhou Xiaogang Zhu Qing-Long Han Lin Li Xiao Chen Sheng Wen Yang Xiang the School of Science Computing and Engineering Technologies Swinburne University of Technology IEEE the School of Computer and Mathematical Sciences the University of Adelaide Adelaide the Faculty of Science and Engineering Southern Cross University the School of Information and Physical Sciences the University of Newcastle

ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential security risks that need to be carefully evaluated and addressed. In this survey, we provide an overview of the current state of research on security of using ChatGPT, with aspects of bias, disinformation, ethics, misuse,attacks and privacy. We review and discuss the literature on these topics and highlight open research questions and future *** this survey, we aim to contribute to the academic discourse on AI security, enriching the understanding of potential risks and mitigations. We anticipate that this survey will be valuable for various stakeholders involved in AI development and usage, including AI researchers, developers, policy makers, and end-users.

关键词： Artificial intelligence (AI) ChatGPT large language models (LLMs) security

来源：评论

学校读者我要写书评

暂无评论

SignBERT+: Hand-Model-Aware Self-Supervised Pre-Training for Sign Language Understanding

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第9期45卷 11221-11239页

作者： Hu, Hezhen Zhao, Weichao Zhou, Wengang Li, Houqiang University of Science and Technology of China Department of Electronic Engineering and Information Science of Electrical and Computer Engineering Anhui Hefei230026 China

Hand gesture serves as a crucial role during the expression of sign language. Current deep learning based methods for sign language understanding (SLU) are prone to over-fitting due to insufficient sign data resource and suffer limited interpretability. In this paper, we propose the first self-supervised pre-trainable SignBERT+ framework with model-aware hand prior incorporated. In our framework, the hand pose is regarded as a visual token, which is derived from an off-the-shelf detector. Each visual token is embedded with gesture state and spatial-temporal position encoding. To take full advantage of current sign data resource, we first perform self-supervised learning to model its statistics. To this end, we design multi-level masked modeling strategies (joint, frame and clip) to mimic common failure detection cases. Jointly with these masked modeling strategies, we incorporate model-aware hand prior to better capture hierarchical context over the sequence. After the pre-training, we carefully design simple yet effective prediction heads for downstream tasks. To validate the effectiveness of our framework, we perform extensive experiments on three main SLU tasks, involving isolated and continuous sign language recognition (SLR), and sign language translation (SLT). Experimental results demonstrate the effectiveness of our method, achieving new state-of-the-art performance with a notable gain. © 1979-2012 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Model-Free Adaptive Frequency Calibration for Voltage-Controlled Oscillators

引用

China Communications 2023年第1期20卷 199-208页

作者： Lianghui Xie Zhi Quan Osama Elnaha Qinglin Zhao Faculty of Information Technology Macao University of Science and TechnologyMacao 999078China College of Electronic Information Engineering Shenzhen UniversityShenzhen 518060China Department of Electrical Engineering Faculty of EngineeringAssiut UniversityEgypt

The operating frequency accuracy of the local oscillators is critical for the overall system performance in the communication ***,the high-precision oscillators could be too expensive for civil *** this paper,we propose a model-free adaptive frequency calibration framework for a voltage-controlled crystal oscillator(VCO)equipped with a time to digital converter(TDC),which can significantly improve the frequency accuracy of the VCO thus *** idea is to utilize a high-precision TDC to directly measure the VCO period which is then passed to a model-free method for working frequency *** advantage of this method is that the working frequency calibration employs the system history of input/output(I/O)data,instead of establishing an accurate VCO voltagecontrolled oscillator *** advantage is the lightweight calibration method with low complexity such that it can be implemented on an MCU with limited computation *** results show that the proposed calibration method can improve the frequency accuracy of a VCO from±20 ppm to±10 ppb,which indicates the promise of the modelfree adaptive frequency calibrator for VCOs.

关键词： frequency calibration carrier frequency offset model-free adaptive control wireless communication systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning Model with Data Augmentation for Arabic Aspect-Based Sentiment Analysis

引用

computers, Materials & Continua 2023年第5期75卷 4419-4444页

作者： Arwa Saif Fadel Osama Ahmed Abulnaja Mostafa Elsayed Saleh Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science Faculty of Computer Sciences and EngineeringHodeidah UniversityYemen

Aspect-based sentiment analysis(ABSA)is a fine-grained *** fundamental subtasks are aspect termextraction(ATE)and aspect polarity classification(APC),and these subtasks are dependent and closely ***,most existing works on Arabic ABSA content separately address them,assume that aspect terms are preidentified,or use a pipeline *** solutions design different models for each task,and the output from the ATE model is used as the input to the APC model,which may result in error propagation among different steps because APC is affected by ATE *** methods are impractical for real-world scenarios where the ATE task is the base task for APC,and its result impacts the accuracy of ***,in this study,we focused on a multi-task learning model for Arabic ATE and APC in which the model is jointly trained on two subtasks simultaneously in a *** paper integrates themulti-task model,namely Local Cotext Foucse-Aspect Term Extraction and Polarity classification(LCF-ATEPC)and Arabic Bidirectional Encoder Representation from Transformers(AraBERT)as a shred layer for Arabic contextual text *** LCF-ATEPC model is based on a multi-head selfattention and local context focus mechanism(LCF)to capture the interactive information between an aspect and its ***,data augmentation techniques are proposed based on state-of-the-art augmentation techniques(word embedding substitution with constraints and contextual embedding(AraBERT))to increase the diversity of the training *** paper examined the effect of data augmentation on the multi-task model for Arabic *** experiments were conducted on the original and combined datasets(merging the original and augmented datasets).Experimental results demonstrate that the proposed Multi-task model outperformed existing APC *** results were obtained by AraBERT and LCF-ATEPC with fusion layer(AR-LCF-ATEPC-Fusion)and the proposed data augmentation

关键词： Arabic aspect extraction arabic sentiment classification AraBERT multi-task learning data augmentation

来源：评论

学校读者我要写书评

暂无评论

Impact of UV content of illumination on acceptability of colour reproduction 12

Impact of UV content of illumination on acceptability of col...

引用

12th Colour and Visual Computing Symposium, CVCS 2024

作者： Nussbaum, Peter Gudzenchuk, Anastasiia Green, Phil Faculty of Information Technology and Electrical Engineering Department of Computer Science NTNU Norway Department of Science and Technology Linköping University Sweden

Paper and board for printing commonly contains optical brightening agents that fluoresce in the presence of UV radiation, making the prints appear brighter and bluer. If the relative amount of optical brightening agents (OBAs) is not consistent between proof and print, and the UV content of measurement and the viewing illumination differs, there will be a colorimetric difference between proof and print. Colour management workflows are normally media-relative, and visual adaptation to the media white can conflict with the goals of colorimetric matching. The impact of UV content in measurement and viewing illumination on the visual acceptability of colour reproductions was investigated in a series of psychophysical experiments, using substrates with varying OBA concentrations and a media-relative colour reproduction workflow. The results showed that visual acceptability was largely unaffected by UV content of measurement or viewing illumination, suggesting that visual adaptation to media white discounts the effect of fluorescence. © 2024 Copyright for this paper by its authors.

关键词： Colorimetry

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review on the Security Attacks and Countermeasures Used in Graphical Passwords

引用

IEEE Access 2024年 12卷 53408-53423页

作者： Por, Lip Yee Ng, Ian Ouii Chen, Yen-Lin Yang, Jing Ku, Chin Soon Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer System and Technology Kuala Lumpur50603 Malaysia National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106344 Taiwan Universiti Tunku Abdul Rahman Department of Computer Science Kampar31900 Malaysia

This systematic literature review delves into the dynamic realm of graphical passwords, focusing on the myriad security attacks they face and the diverse countermeasures devised to mitigate these threats. The core objective of this paper is to identify existing security threats to graphical password schemes and the corresponding countermeasures developed to mitigate these attacks. The study process begins by identifying the usable databases and search engines to identify all the relevant resources. The inclusion and exclusion criteria were carefully selected to prioritize the study, focusing mostly on attacks and countermeasures related to graphical password schemes between 2009 and 2023. After thorough identification and selection progress, 59 studies met all the criteria. Among these studies, 47 mentioned shoulder surfing as a threat to graphical password schemes, while 20 discussed brute force attacks. Additionally, there were 21 papers on dictionary attacks, 13 on smudge attacks, spyware attacks, and social engineering, and 19 that discussed guessing attacks as threats to graphical password schemes. Furthermore, the papers identified several other attacks, including frequency of occurrence analysis attacks, video recording, eavesdropping, computer vision, sonar, and image gallery attacks, with the corresponding numbers of papers being 9, 17, 5, 2, 2, and 1, respectively. The results also highlight the countermeasures proposed in the study papers to mitigate the aforementioned attacks. Among the various countermeasures identified, most revolve around randomization, obfuscation, and password space complexity as the most commonly used techniques for enhancing the security of graphical password schemes. © 2013 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Efficient Saliency Map Detection for Low-Light Images Based on Image Gradient

引用

IEEE Transactions on Circuits and Systems for Video technology 2024年第2期34卷 852-865页

作者： Lin, Chun-Yi Haq, Muhamad Amirul Chen, Jiun-Han Ruan, Shanq-Jang Naroska, Edwin National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei10607 Taiwan Hochschule Niederrhein University of Applied Science Faculty of Electrical Engineering and Computer Science Krefeld47805 Germany

Recently, deep learning has been widely employed across various domains. The Convolution Neural Network (CNN), a popular deep learning algorithm, has been successfully utilized in object recognition tasks, such as face recognition, vehicle recognition, and license plate recognition. However, conventional methods for object recognition may not be appropriate for low-light image recognition due to information loss in the dark regions and unexpected noise that can impair object quality. Therefore, the development of specialized techniques for low-light image enhancement has become a major research focus for object detection. This paper proposed a gradient-based saliency map detection method with an improved ResNet architecture that outperforms previous works in detecting multiple or large objects. Additionally, the proposed method enhances images with the object as the center and emphasizes foreground-background differences. Compared with previous works, this paper achieves1.28× improvements in the parameters and 1.32× faster inference speed than the original ResNet architecture. © 1991-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancing Bankruptcy Forecasting With Hybrid Machine Learning Techniques: Insights From an Unbalanced Polish Dataset

引用

IEEE Access 2024年 12卷 9369-9381页

作者： Ainan, Ummey Hany Por, Lip Yee Chen, Yen-Lin Yang, Jing Ku, Chin Soon Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer System and Technology Kuala Lumpur50603 Malaysia National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106344 Taiwan Universiti Tunku Abdul Rahman Department of Computer Science Kampar31900 Malaysia

The challenge of bankruptcy prediction, critical for averting financial sector losses, is amplified by the prevalence of imbalanced datasets, which often skew prediction models. Addressing this, our study introduces the innovative hybrid model XGBoost+ANN, designed to leverage the strengths of both ensemble learning and artificial neural networks. This model integrates a comprehensive set of features with parameters optimized through genetic algorithms, eschewing traditional feature selection approaches. Our research focuses on an unbalanced dataset of Polish companies and reveals that the XGBoost+ANN model, in particular, exhibits outstanding performance. Optimized using genetic algorithms and without feature selection, this model achieved the highest AUC (0.958), sensitivity (0.752), and accuracy (0.983) scores, surpassing other models in our study. This remarkable outperformance, along with the robust results, marks a substantial advancement in the field of bankruptcy prediction. It underscores the efficacy of our approach in addressing the persistent challenge of data imbalance, offering a more reliable and accurate solution for financial risk assessment. © 2013 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Optimal DPM Based Energy-Aware Task Scheduling for Performance Enhancement in Embedded MPSoC

引用

computers, Materials & Continua 2023年第1期74卷 2097-2113页

作者： Hamayun Khan Irfan Ud Din Arshad Ali Mohammad Husain Department of Electrical Engineering Faculty of Engineering&Technology Superior University Lahore54000Pakistan Department of Computer Science Faculty of Computer Science&IT Superior University Lahore54000Pakistan Faculty of Computer and Information Systems Islamic University of MadinahAl Madinah Al Munawarah42351Saudi Arabia

Minimizing the energy consumption to increase the life span and performance of multiprocessor system on chip(MPSoC)has become an integral chip design issue for multiprocessor *** performance measurement of computational systems is changing with the advancement in *** to shrinking and smaller chip size power densities onchip are increasing rapidly that increasing chip temperature in multi-core embedded *** operating speed of the device decreases when power consumption reaches a threshold that causes a delay in complementary metal oxide semiconductor(CMOS)circuits because high on-chip temperature adversely affects the life span of the *** this paper an energy-aware dynamic power management technique based on energy aware earliest deadline first(EA-EDF)scheduling is proposed for improving the performance and reliability by reducing energy and power consumption in the system on chip(SOC).Dynamic power management(DPM)enables MPSOC to reduce power and energy consumption by adopting a suitable core configuration for task *** migration avoids peak temperature values in the multicore *** utilization factor(ui)on central processing unit(CPU)core consumes more energy and increases the temperature *** technique switches the core bymigrating such task to a core that has less temperature and is in a low power *** proposed EA-EDF scheduling technique migrates load on different cores to attain stability in temperature among multiple cores of the CPU and optimized the duration of the idle and sleep periods to enable the low-temperature *** effectiveness of the EA-EDF approach reduces the utilization and energy consumption compared to other existing methods and *** simulation results show the improvement in performance by optimizing 4.8%on u_(i) 9%,16%,23%and 25%at 520 MHz operating frequency as compared to other energy-aware techniques for MPSoCs when the least number of tasks is in running state and can

关键词： Dynamic power management dynamic voltage&frequency scaling dynamic thermal management multiprocessor system on chip complementary metal oxide semiconductor reliability

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Hybrid Model Based on CNN and BiLSTM for Identifying Individuals via Handwriting Analysis

引用

computer Modeling in engineering & sciences 2024年第8期140卷 1689-1710页

作者： Md.Abdur Rahim Fahmid Al Farid Abu Saleh Musa Miah Arpa Kar Puza Md.Nur Alam Md.Najmul Hossain Sarina Mansor Hezerul Abdul Karim Department of Computer Science and Engineering Pabna University of Science and TechnologyPabna6600Bangladesh Faculty of Engineering Multimedia UniversityCyberjaya63100Malaysia Department of Computer Science and Engineering Bangladesh Army University of Science and TechnologySaidpur5311Bangladesh Department of Mathematics Pabna University of Science and TechnologyPabna6600Bangladesh Department of Electrical Electronic and Communication EngineeringPabnaUniversity of Science and TechnologyPabna6600Bangladesh Department of Electrical and Communication Engineering Pabna University of Science and TechnologyPabna6600Bangladesh

Handwriting is a unique and significant human feature that distinguishes them from one *** are many researchers have endeavored to develop writing recognition systems utilizing specific signatures or symbols for person identification through ***,such systems are susceptible to forgery,posing security *** response to these challenges,we propose an innovative hybrid technique for individual identification based on independent handwriting,eliminating the reliance on specific signatures or *** response to these challenges,we propose an innovative hybrid technique for individual identification based on independent handwriting,eliminating the reliance on specific signatures or *** innovative method is intricately designed,encompassing five distinct phases:data collection,preprocessing,feature extraction,significant feature selection,and *** key advancement lies in the creation of a novel dataset specifically tailored for Bengali handwriting(BHW),setting the foundation for our comprehensive ***-preprocessing,we embarked on an exhaustive feature extraction process,encompassing integration with kinematic,statistical,spatial,and composite *** meticulous amalgamation resulted in a robust set of 91 *** enhance the efficiency of our system,we employed an analysis of variance(ANOVA)F test and mutual information scores approach,meticulously selecting the most pertinent *** the identification phase,we harnessed the power of cutting-edge deep learning models,notably the Convolutional Neural Network(CNN)and Bidirectional Long Short-Term Memory(BiLSTM).These models underwent rigorous training and testing to accurately discern individuals based on their handwriting ***,our methodology introduces a groundbreaking hybrid model that synergizes CNN and BiLSTM,capitalizing on fine motor features for enhanced individual ***,our experimental results unde

关键词： Bengali handwriting(BHW) person identification convolutional neural network(CNN) BiLSTM

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：