检索结果-内蒙古大学图书馆

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Jhonatan Geremias Eduardo K. Viegas Altair O. Santin Alceu Britto Pedro Horchulhack Pontificia Universidade Catolica do Parana (PUCPR) - Graduate Program in Computer Science (PPGIa) Brazil Secure Systems Research Center - Technology Innovation Institute (TII) Abu Dhabi

Over the last years, several works have proposed highly accurate Android malware detection techniques. Surprisingly, modern malware apps can still pave their way to official markets, thus, demanding the provision of more robust and accurate detection approaches. This paper proposes a new multi-view Android malware detection through image-based deep learning, implemented threefold. First, apps are evaluated according to several feature sets in a multi-view setting, thus, increasing the information provided for the classification task. Second, extracted feature sets are converted to an image format while maintaining the principal components of the data distribution, keeping the information for the classification task. Third, built images are jointly represented in a single shot, each in a predefined image channel, enabling the application of deep learning architectures. Experiments on a new version of a publicly available Android malware dataset composed of over 11 thousand Android apps have shown our proposal's feasibility. It reaches true-negative rates of up to 99.5% when implemented with a single-view approach with our new image-building technique. In addition, if our proposed multi-view scheme is used, the classification accuracies of malware families become more stable, reaching a true-positive rate of up to 98.7%.

关键词： Deep learning Wireless communication Buildings computer architecture Feature extraction Malware Proposals

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Model Updates Through GAN Data Augmentation and Transfer Learning

Intrusion Detection Model Updates Through GAN Data Augmentat...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Pedro Horchulhack Eduardo K. Viegas Altair O. Santin Jhonatan Geremias Pontificia Universidade Catolica do Parana (PUCPR) ― Graduate Program in Computer Science (PPGIa) Brazil Secure Systems Research Center ― Technology Innovation Institute (TII) Abu Dhabi

ISBN: (纸本)9781665435413

Current machine learning techniques for network-based intrusion detection cannot handle the evolving behavior of network traffic, requiring periodic model updates to be conducted. Besides requiring huge amounts of labeled network traffic to be provided, traditional model updates demand expressive computational costs. This paper proposes a new feasible model update procedure implemented in two steps. First, we use a Generative Adversarial Network (GAN) to augment the sampled network traffic. Next, we use the augmented dataset to perform model updates through a transfer learning-based approach. Thus, our model can decrease both the number of instances that must be labeled and the computational costs during model updates. Our experiments on a one-year dataset with over 8 TB of data show that literature techniques cannot handle changes in network traffic behavior. In contrast, the proposed model without updates improved true-positive rates by up to 25.6%. With monthly model updates, it requires only 14% of computational costs and 2.3% of instances to be provided.

关键词： Computational modeling Transfer learning Intrusion detection Telecommunication traffic Generative adversarial networks Data models Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards Adversarial Robustness for Multi-Mode Data through Metric Learning

引用

Sensors 2023年第13期23卷 6173-6173页

作者： Khan, Sarwar Chen, Jun-Cheng Liao, Wen-Hung Chen, Chu-Song Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Social Networks Human-Centered Computing Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan Department of Computer Science National Chengchi University Taipei11605 Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei106319 Taiwan

Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial training, which is currently one of the most effective defense methods, mainly focus on the single-mode setting and thus fail to capture the full data representation to defend against adversarial attacks. To confront this challenge, we propose a novel multi-prototype metric learning regularization for adversarial training which can effectively enhance the defense capability of adversarial training by preventing the latent representation of the adversarial example changing a lot from its clean one. With extensive experiments on CIFAR10, CIFAR100, MNIST, and Tiny ImageNet, the evaluation results show the proposed method improves the performance of different state-of-the-art adversarial training methods without additional computational cost. Furthermore, besides Tiny ImageNet, in the multi-prototype CIFAR10 and CIFAR100 where we reorganize the whole datasets of CIFAR10 and CIFAR100 into two and ten classes, respectively, the proposed method outperforms the state-of-the-art approach by 2.22% and 1.65%, respectively. Furthermore, the proposed multi-prototype method also outperforms its single-prototype version and other commonly used deep metric learning approaches as regularization for adversarial training and thus further demonstrates its effectiveness. © 2023 by the authors.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Fusion of Mixture of Experts and Generative Artificial Intelligence in Mobile Edge Metaverse

arXiv

引用

arXiv 2024年

作者： Liu, Guangyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Mao, Shiwen Kim, Dong In The College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Auburn University Auburn United States The School of Electrical and Computer Engineering University of Sydney Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is slowed down by the challenges of content creation, scalability, and dynamic user interaction. Our study investigates an integration of Mixture of Experts (MoE) models with Generative Artificial Intelligence (GAI) for mobile edge computing to revolutionize content creation and interaction in the Metaverse. Specifically, we harness an MoE model's ability to efficiently manage complex data and complex tasks by dynamically selecting the most relevant experts running various sub-models to enhance the capabilities of GAI. We then present a novel framework that improves video content generation quality and consistency, and demonstrate its application through case studies. Our findings underscore the efficacy of MoE and GAI integration to redefine virtual experiences by offering a scalable, efficient pathway to harvest the Metaverse's full potential. © 2024, CC BY.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Discovering an aid policy to minimize student evasion using offline reinforcement learning

arXiv

引用

arXiv 2021年

作者： De Lima, Leandro M. Krohling, Renato A. Graduate Program in Computer Science PPGI Federal University of Espirito Santo UFES Vitória Brazil Graduate Program in Computer Science PPGI Production Engineering Department LABCIN Federal University of Espirito Santo UFES Vitória Brazil

High dropout rates in tertiary education expose a lack of efficiency that causes frustration of expectations and financial waste. Predicting students at risk is not enough to avoid student dropout. Usually, an appropriate aid action must be discovered and applied in the proper time for each student. To tackle this sequential decision-making problem, we propose a decision support method to the selection of aid actions for students using offline reinforcement learning to support decision-makers effectively avoid student dropout. Additionally, a discretization of student's state space applying two different clustering methods is evaluated. Our experiments using logged data of real students shows, through off-policy evaluation, that the method should achieve roughly 1.0 to 1.5 times as much cumulative reward as the logged policy. So, it is feasible to help decision-makers apply appropriate aid actions and, possibly, reduce student dropout. © 2021, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

To Sharpen or not to Sharpen? On the Effect of Sharpening Filters Applied to Magnified Images 14

To Sharpen or not to Sharpen? On the Effect of Sharpening Fi...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Emmendorfer, Leonardo R. de Olviveira, Vinicius Menezes Schein, Tatiana T. de Jesus, Junior C. Rodriguez, Bárbara D.A. Electrical Energy Processing Department Federal University of Santa Maria 97105-340 Brazil Center for Computational Science Federal University of Rio Grande 96201-900 Brazil Computational Modeling PhD Program Federal University of Rio Grande 96201-900 Brazil Computer Engineering Graduate Program Federal University of Rio Grande 96201-900 Brazil Institute of Mathematics Statistics and Physics Federal University of Rio Grande 96201-900 Brazil

ISBN: (纸本)9781510657564

Super-resolution algorithms aim to produce magnified high-resolution versions from low-resolution images. Some methods, however, are prone to generate blur during the process. Simple sharpening filters are adopted to alleviate this type of artifact. However, the actual effectiveness of this approach is not clear-cut in the literature. This work evaluates the effect of three simple sharpening filters on the quality of images obtained from super-resolution methods. Two metrics were considered in the evaluation: the Peak signal-to-noise ratio (PSNR) metric, and the Learned Perceptual Image Patch Similarity (LPIPS). One of the filters could consistently improve the LPIPS metric of magnified images from diverse benchmark sets on top of seven super-resolution methods. The increments obtained for the perceptual metric seem to occur due to the sharpening effect. Improvements on PSNR values were not as consistent. © 2022 SPIE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Predicting User Preferences with Neural Network Learning to Rank Method 5

Predicting User Preferences with Neural Network Learning to ...

引用

5th IEEE International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2021

作者： Qomariyah, Nunung Nurul Fajar, Ahmad Nurul Bina Nusantara University Faculty Of Computing And Media Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program-Master Of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781665401968

User preference learning has been around for many years. This is a common problem arise in e-commerce system, where the companies need to understand their customers in order to sell the correct products to their target customers. The user preference is also needed in the movie domain area, as the film companies who produce the movie also need to understand how the customers value their movie products, whether the market like it or not. This can help them to predict the best components for the future movie. In order to produce the recommendation to the customer, we can show a list of item in a correct order, sorted from the most relevant/the most liked one to the most irrelevant item. In this paper, we utilize the Learning to Rank (LTR) approach from information retrieval domain area to learn the user preference in recommender system domain. We applied LTR with pairwise approach from the two most popular algorithms in this area, i.e. RankNet and LambdaRank, on 25, 345 user ratings from 5, 000 movie dataset and evaluate both algorithms. We used a Neural Network architecture as the learning mechanism. We also measuring the speed performance of the two algorithms. © 2021 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Multi-class Weather Forecasting from Twitter Using Machine Learning Aprroaches

引用

Procedia computer science 2021年 179卷 47-54页

作者： Kartika Purwandari Join W.C. Sigalingging Tjeng Wawan Cenggoro Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Database Center Division of BMKG Meteorological Climatological and Geophysical Agency Jakarta Indonesia 10720 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

Now in the era of big data, many are applying information methods accurately especially by social media. The aims of this study to classify the weather based on Twitter automatically using text mining by using Support Vector Machine (SVM), MultinomialNaive Bayes (MNB), and Logistic Regression (LR) method. The experimental results show that SVM substantially outperforms various other machine learning algorithms for the task of text classification with an accuracy value of 93%. This result proves that SVM is very suitable for text categorization. We use clustering technique to read the pattern in customers’ opinion about the restaurant based on some measurement variables.

关键词： weather classification twitter machine learning support vector machine multinomial naive bayes logistic regression

来源：评论

学校读者我要写书评

暂无评论

IndoBERT for classifying hate speech in Twitter

引用

AIP Conference Proceedings 2024年第1期3026卷

作者： Hendri Santosa Fatahillah Rachman Stanley Armando Austen Christianto Abba Suganda Girsang Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

Any form of communication that expresses hatred, prejudice, or hostility toward a particular individual or group of people based on attributes such as their race, religion, ethnicity, nationality, gender, sexual orientation, disability, or other protected characteristics is considered hate speech. Hate speech can be verbal, written, or symbolic. Hate speech can take many forms, and it often involves derogatory language, offensive stereotypes, or the incitement of violence or discrimination against the targeted individuals or groups. The content of hate speech is easy found in forum or discussion in social media include twitter. Twitter is a microblogging-based virtual entertainment where clients can peruse and compose text called tweets or tweets. This exploration executes order of disdain discourse in media Twitter utilizing IndoBERT. IndoBERT is the Indonesian form of BERT model utilizing over 220M words. It was a Convolutional Neural Network-based algorithm that had been modified. Th highlight extraction in Transformer isn’t finished by convolution utilizing a part like CNN, however includes an encoder and decoder. The outcome demonstrates IndoBERT’s excellent ability to categorize hate speech.

关键词：

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：