检索结果-内蒙古大学图书馆

Local Adaptive Gradient Variance Attack for Deep Fake Fingerprint Detection

computers, Materials & Continua 2024年第1期78卷 899-914页

作者： Chengsheng Yuan Baojie Cui Zhili Zhou Xinting Li Qingming Jonathan Wu Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Institute of Artificial Intelligence and Blockchain Guangzhou UniversityGuangzhou510006China School of International Relations National University of Defense TechnologyNanjing210039China Department of Electrical and Computer Engineering University of WindsorWindsorN9B 3P4Canada

In recent years,deep learning has been the mainstream technology for fingerprint liveness detection(FLD)tasks because of its remarkable ***,recent studies have shown that these deep fake fingerprint detection(DFFD)models are not resistant to attacks by adversarial examples,which are generated by the introduction of subtle perturbations in the fingerprint image,allowing the model to make fake *** of the existing adversarial example generation methods are based on gradient optimization,which is easy to fall into local optimal,resulting in poor transferability of adversarial *** addition,the perturbation added to the blank area of the fingerprint image is easily perceived by the human eye,leading to poor visual *** response to the above challenges,this paper proposes a novel adversarial attack method based on local adaptive gradient variance for *** ridge texture area within the fingerprint image has been identified and designated as the region for perturbation ***,the images are fed into the targeted white-box model,and the gradient direction is optimized to compute gradient ***,an adaptive parameter search method is proposed using stochastic gradient ascent to explore the parameter values during adversarial example generation,aiming to maximize adversarial attack *** results on two publicly available fingerprint datasets show that ourmethod achieves higher attack transferability and robustness than existing methods,and the perturbation is harder to perceive.

关键词： FLD adversarial attacks adversarial examples gradient optimization transferability

来源：评论

学校读者我要写书评

暂无评论

Silver Lining in the Fake News Cloud: Can Large Language Models Help Detect Misinformation?

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 14-24页

作者： Kumar, Raghvendra Goddu, Bhargav Saha, Sriparna Jatowt, Adam Indian Institute of Technology Department of Computer Science and Engineering Patna801106 India University of Innsbruck Department of Computer Science Innsbruck6020 Austria

In the times of advanced generative artificial intelligence, distinguishing truth from fallacy and deception has become a critical societal challenge. This research attempts to analyze the capabilities of large language models (LLMs) for detecting misinformation. Our study employs a versatile approach, covering multiple LLMs with few- and zero-shot prompting. These models are rigorously evaluated across various fake news and rumor detection datasets. Introducing a novel dimension, we additionally incorporate sentiment and emotion annotations to understand the emotional influence on misinformation detection using LLMs. Moreover, to extend our inquiry, we employ ChatGPT to intentionally distort authentic news as well as human-written fake news, utilizing zero-shot and iterative prompts. This deliberate corruption allows for a detailed examination of various parameters such as abstractness, concreteness, and named entity density, providing insights into differentiating between unaltered news, human-written fake news, and its LLM-corrupted counterpart. Our findings aspire to furnish a refined framework for discerning authentic news, human-generated misinformation, and LLM-induced distortions. This multifaceted approach, utilizing various prompt techniques, contributes to a comprehensive understanding of the subtle variations shaping misinformation sources. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Visual quality-enhanced reversible data hiding scheme based on interpolation and variant Sudoku matrics

引用

Multimedia Tools and Applications 2025年第18期84卷 20219-20247页

作者： Yuan, Longfei Lin, Chia-Chen Chang, Chin-Chen Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung Taiwan Department of Information Engineering and Computer Science Feng Chia University Taichung Taiwan

Utilizing interpolation techniques (IT) within reversible data hiding (RDH) algorithms presents the advantage of a substantial embedding capacity. Nevertheless, prevalent algorithms often straightforwardly embed confidential data into non-reference pixels without accounting for the relationships between neighboring pixels. This practice results in suboptimal visual quality in the stego images. To rectify this issue, we have introduced the augmentation and modification interpolation (AMI). Additionally, we have devised two variant Sudoku matrices to facilitate distinct data-hiding strategies tailored for different types of reference pixels: Single type and Paired type. By incorporating these innovative designs, the interpolation operation now preserves the pattern-level information of the block in the original image, rather than focusing solely on the pixel level. In assessing the effectiveness of our proposed scheme, we performed experiments utilizing two representative image datasets. The outcomes of these experiments validate that our scheme attains an average PSNR of 44.11 dB and an average hiding capacity of 1.63 bpp. Consequently, it is affirmed that the advantage offered by our proposed scheme is well-suited for scenarios demanding high-quality stego images. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

The Elevated Temperature Tribological Performance of Tough and Superhard TaMoN-Ag Films With Solute and Nanocomposite Structures

引用

Journal of Tribology 2025年第6期147卷 062101页

作者： Wang, Huiying Li, Hang Li, Jianliang Wei, Ningxin Sun, Longlong Huang, Jiewen Kong, Jian Wu, Qiujie Shi, Yan Department of Materials Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Materials Science and Engineering Hubei Polytechnic University Huangshi435003 China College of Materials and Metallurgy Guizhou University Guiyang550025 China

Films have been prepared with not only high hardness to guarantee excellent wear resistance but also high toughness to prevent brittle fracture at low to middle-high temperatures. On the basis of ternary transition metal nitrides with significantly improved hardness and toughness, TaMoN-Ag films with solute and nanocomposite structure were prepared by direct current (DC) magnetron sputtering technology. Friction wear tests were performed between room temperature (RT) and 700 °C. When doping with trace amounts of Ag atoms (∼1.12 at%, 4 W), TaMoN-Ag film maintain solid solution structure. TaMoN-Ag films with the Ag target power is 4 W show the highest hardness (H ∼62.1 GPa), which is 58% higher than TaMoN film and 44% better than that of TaMoN films. Meanwhile, a lower wear rate (KIC ∼5.87 × 10-7 mm3/N·m) is obtained. The tribological properties of TaMoN-Ag films at room temperatures are related to the H3/E2 and lubricious Ag phase, while the tribological properties at high temperatures are mainly due to the formation of lubricating binary metal oxides (AgxTMyOz (Magnéli phases)). The composite films generally have good resistance to plastic deformation. © 2024 by ASME.

关键词： Nanocomposite films

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Cloud Security: Innovative Attack Detection and Privacy Focused Key Management

引用

IEEE Transactions on computers 2025年第6期74卷 1978-1989页

作者： Ahmad, Shahnawaz Arif, Mohd Mehfuz, Shabana Ahmad, Javed Nazim, Mohd Bennett University School of Computer Science Engineering and Technology Greater Noida201310 India Galgotias University School of Computer Science & Engineering Greater Noida203201 India Jamia Millia Islamia Department of Electrical Engineering New Delhi110025 India Sharda University Department of Computer Science and Engineering Sharda School of Engineering and Technology Greater Noida201310 India Noida Institute of Engineering and Technology Department of Computer Science and Engineering School of Computer Science and IT Greater Noida201306 India

Cloud Computing (CC) is widely adopted in sectors like education, healthcare, and banking due to its scalability and cost-effectiveness. However, its internet-based nature exposes it to cyber threats, necessitating advanced security frameworks. Traditional models suffer from high false positives and limited adaptability. To address these challenges, VECGLSTM, an attack detection model integrating Variable Long Short-Term Memory (VLSTM), capsule networks, and the Enhanced Gannet Optimization Algorithm (EGOA), is introduced. This hybrid approach enhances accuracy, reduces false positives, and dynamically adapts to evolving threats. EGOA is employed for its superior optimization capability, ensuring faster convergence and resilience. Additionally, Chaotic Cryptographic Pelican Tunicate Swarm Optimization (CCPTSO) is proposed for privacy-preserving key management. This model combines chaotic cryptographic techniques with the Pelican Tunicate Swarm Optimization Algorithm (PTSOA), leveraging the pelican algorithm’s exploration strength and the tunicate swarm’s exploitation ability for optimal encryption security. Performance evaluation demonstrates 99.675% accuracy, 99.5175% recall, 99.7075% precision, and 99.615% F1-score, along with reduced training (1.79s), encryption (0.986s), and decryption (1.029s) times. This research significantly enhances CC security by providing a scalable, adaptive framework that effectively counters evolving cyber threats while ensuring efficient key management. © 1968-2012 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Phasmatodea Population Evolution Algorithm Based on Spiral Mechanism and Its Application to Data Clustering

引用

computers, Materials & Continua 2025年第4期83卷 475-496页

作者： Jeng-Shyang Pan Mengfei Zhang Shu-Chuan Chu Xingsi Xue Václav Snášel College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China Department of Information Management Chaoyang University of TechnologyTaichung41349TaiwanChina Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Faculty of Electrical Engineering and Computer Science VŠB-Technical University of OstravaOstrava70833Czech Republic

Data clustering is an essential technique for analyzing complex datasets and continues to be a central research topic in data *** clustering algorithms,such as K-means,are widely used due to their simplicity and *** paper proposes a novel Spiral Mechanism-Optimized Phasmatodea Population Evolution Algorithm(SPPE)to improve clustering *** SPPE algorithm introduces several enhancements to the standard Phasmatodea Population Evolution(PPE)***,a Variable Neighborhood Search(VNS)factor is incorporated to strengthen the local search capability and foster population ***,a position update model,incorporating a spiral mechanism,is designed to improve the algorithm’s global exploration and convergence ***,a dynamic balancing factor,guided by fitness values,adjusts the search process to balance exploration and exploitation *** performance of SPPE is first validated on CEC2013 benchmark functions,where it demonstrates excellent convergence speed and superior optimization results compared to several state-of-the-art metaheuristic *** further verify its practical applicability,SPPE is combined with the K-means algorithm for data clustering and tested on seven *** results show that SPPE-K-means improves clustering accuracy,reduces dependency on initialization,and outperforms other clustering *** study highlights SPPE’s robustness and efficiency in solving both optimization and clustering challenges,making it a promising tool for complex data analysis tasks.

关键词： Phasmatodea population evolution algorithm data clustering meta-heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Synthesis of monolayer tungsten nitride:Rapid optical visualization and electrical impact of grain boundaries

引用

Nano Research 2025年第3期18卷 645-653页

作者： Qiuyun Yang Dehu Li Fanfan Shi Zhibin Shao Na Wang Yao Peng Edwin Hang Tong Teo Zheng Liu Hong Wang Department of Physics University of Science and Technology of ChinaHefei 230026China Institute of Electrical and Electronic Engineering Anhui Science and Technology UniversityFengyang 233100China College of Mechanics and Engineering Science Hohai UniversityNanjing 211100China School of Materials Science and Engineering Nanyang Technological University50 Nanyang AvenueSingapore 639798Singapore

Two-dimensional(2D)transition metal nitrides(TMNs)have garnered significant attention in fields such as energy storage and nanoelectronics due to their unique electrical properties,high chemical stability,and excellent mechanical *** polycrystalline 2D TMNs films,grain boundaries(GBs)are inevitable structural defects that could play a crucial role in determining the material's *** rapid optical visualization methods is essential for obtaining large-scale information on the distribution of ***,the rapid visualization of GBs in 2D TMNs,as well as the impact of GBs on the material's electrical properties,has never been previously *** this study,we demonstrate the growth of monolayer tungsten nitride crystals on SiO_(2)/Si substrates by chemical vapor deposition(CVD).High-resolution transmission electron microscopy reveals the presence of GBs at the junctions of twisted grains.A wet-etch process utilizing buffered oxide etchant(BOE)enables rapid and effective visualization of these GBs with optical *** analyzing grains with different twist angles,we find that GBs at specific angles demonstrate increased stability during *** measurements revealed that tilted GBs hinder electrical transport,with GBs of a 62°twist angle showing sheet conductance nearly half that within the monolayer *** work not only provides insights into GBs in monolayer tungsten nitride but also lays the groundwork for exploring GBs-related properties in other 2D TMNs.

关键词： two-dimensional(2D)materials grain boundary chemical vapor deposition electrical property tungsten nitride

来源：评论

学校读者我要写书评

暂无评论

Modeling Task Engagement to Regulate Reinforcement Learning-based Decoding for Online Brain Control

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期17卷 606-614页

作者： Zhang, Xiang Shen, Xiang Wang, Yiwen Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Chemical and Biological Engineering Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Brain-Machine Interfaces (BMIs) offer significant promise for enabling paralyzed individuals to control external devices using their brain signals. One challenge is that during the online Brain Control (BC) process, subjects may not be completely immersed in the task, particularly when multiple steps are needed to achieve a goal. The decoder indiscriminately takes the less engaged trials as training data, which might decrease the decoding accuracy. In this paper, we propose an alternative kernel RL-based decoder that trains online with continuous parameter update. We model neural activity from the medial prefrontal cortex (mPFC), a reward-related brain region, to represent task engagement. This information is incorporated into a stochastic learning rate using an exponential model, which measures the relevancy of neural data. The proposed algorithm was evaluated in the experiment where rats performed a cursor-reaching BC task. We found the neural activities from mPFC contained the engagement information which was negatively correlated with trial response time. Moreover, compared to the RL method without task engagement modeling, our proposed method enhanced the training efficiency. It used half of the training data to achieve the same reconstruction accuracy of the cursor trajectory. The results demonstrate the potential of our RL framework for improving online brain control tasks. © 2016 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SeBROP:blind ROP attacks without returns

引用

Frontiers of computer science 2022年第4期16卷 185-202页

作者： Tianning Zhang Miao Cai Diming Zhang Hao Huang Department of Computer Science and Technology Nanjing UniversityNanjing210023China School of Computer and Information Hohai UniversityNanjing211106China College of Computer Engineering Jiangsu University of Science and TechnologyZhenjiang212008China

Currently,security-critical server programs are well protected by various defense techniques,such as Address Space Layout Randomization(ASLR),eXecute Only Memory(XOM),and Data Execution Prevention(DEP),against modern code-reuse attacks like Return-oriented Programming(ROP)***,in these victim programs,most syscall instructions lack the following ret instructions,which prevents attacks to stitch multiple system calls to implement advanced behaviors like launching a remote *** this kind of gadget greatly constrains the capability of code-reuse *** paper proposes a novel code-reuse attack method called Signal Enhanced Blind Return Oriented Programming(SeBROP)to address these *** SeBROP can initiate a successful exploit to server-side programs using only a stack overflow *** leveraging a side-channel that exists in the victim program,we show how to find a variety of gadgets blindly without any pre-knowledges or reading/disassembling the code ***,we propose a technique that exploits the current vulnerable signal checking mechanism to realize the execution flow control even when ret instructions are *** technique can stitch a number of system calls without returns,which is more superior to conventional ROP ***,the SeBROP attack precisely identifies many useful gadgets to constitute a Turing-complete *** attack can defeat almost all state-of-the-art defense *** SeBROP attack is compatible with both modern 64-bit and 32-bit *** validate its effectiveness,We craft three exploits of the SeBROP attack for three real-world applications,i.e.,32-bit Apache 1.3.49,32-bit ProFTPD 1.3.0,and 64-bit Nginx *** results demonstrate that the SeBROP attack can successfully spawn a remote shell on Nginx,ProFTPD,and Apache with less than 8500/4300/2100 requests,respectively.

关键词： code-reuse atack ROP signal

来源：评论

学校读者我要写书评

暂无评论

Enhanced thyroid disease prediction using ensemble machine learning: a high-accuracy approach with feature selection and class balancing

引用

Discover Artificial Intelligence 2025年第1期5卷 1-29页

作者： Islam, Md. Rezaul Chowdhury, Aniruddha Islam Shama, Sharmin Lamyea, Md. Masudul Hasan Department of Computer Science and Engineering Shahjalal University of Science and Technology Sylhet3114 Bangladesh Department of Educational Technology and Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Gazipur1750 Bangladesh Department of Computer Science and Engineering Dhaka International University Dhaka1212 Bangladesh

Thyroid disorders are increasingly prevalent, making early detection crucial for reducing mortality and complications. Accurate prediction of disease progression and understanding the interplay of clinical features are essential for effective diagnosis and treatment. Our study addresses these challenges by employing a standard machine learning model, enhanced with comprehensive clinical feature analysis and an ensemble learning technique. By leveraging machine learning, we can identify key risk factors and improve diagnostic accuracy. To achieve optimal prediction outcomes, we evaluated seventeen machine learning models and implemented an Ensemble ML classifier using a hard voting strategy. Class balancing techniques, particularly random oversampling, significantly improved classification performance. Our experimental results demonstrate that the proposed model outperforms existing methods, achieving 100% sensitivity and 99.72% accuracy using the XGBoost algorithm and SelectKBest feature selection. By addressing feature reduction and high class-imbalance, the ensemble ML classifier with hard voting proves more effective in handling classification challenges. © The Author(s) 2025.

关键词： Adversarial machine 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：