2022 56th Annual Conference on Information Sciences and Systems (CISS)最新文献_第3页

Doubly-Rational Series: Recognizability and Realizations 二重有理级数:认识与实现

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751193

G. Venkatesh

引用次数: 0

A Non-Zero Sum Bandwidth Scanning Game with a Sophisticated Adversary 一个非零和带宽扫描游戏与一个复杂的对手

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751180

A. Garnaev, W. Trappe

引用次数: 0

Sequential Recommendation Using Deep Reinforcement Learning and Multi-Head Attention 使用深度强化学习和多头注意的顺序推荐

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751174

Raneem Sultan, Mervat Abu-Elkheir

引用次数: 1

Differentially Private Federated Learning with Drift Control 差分私有联邦学习与漂移控制

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751200

Wei-Ting Chang, Mohamed Seif, R. Tandon

{"title":"Differentially Private Federated Learning with Drift Control","authors":"Wei-Ting Chang, Mohamed Seif, R. Tandon","doi":"10.1109/CISS53076.2022.9751200","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751200","url":null,"abstract":"In this paper, we consider the problem of differentially private federated learning with statistical data heterogeneity. More specifically, users collaborate with the parameter server (PS) to jointly train a machine learning model using their local datasets that are non-i.i.d. across users. The PS is assumed to be honest-but-curious so that the data at users need to be kept private from the PS. More specifically, interactions between the PS and users must satisfy differential privacy (DP) for each user. In this work, we propose a differentially private mechanism that simultaneously deals with user-drift caused by non-i.i.d. data and the randomized user participation in the training process. Specifically, we study SCAFFOLD, a popular federated learning algorithm, that has shown better performance on dealing with non-i.i.d. data than previous federated averaging algorithms. We study the convergence rate of SCAFFOLD under differential privacy constraint. Our convergence results take into account time-varying perturbation noises used by the users, and data and user sampling. We propose two time-varying noise allocation schemes in order to achieve better convergence rate and satisfy a total DP privacy budget. We also conduct experiments to confirm our theoretical findings on real world dataset.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128743988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rate Region of the One-Help-Two Quadratic Gaussian Source-Coding Problem with Markovity 带Markovity的一助二二次高斯源编码问题的速率域

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751169

O. Bilgen, A. Wagner

引用次数: 0

Development of Anomalous Video Detection System using Hybrid-Features Analysis of Actions and Scene-Backgrounds Information 基于动作和场景背景信息混合特征分析的异常视频检测系统的开发

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751197

Bharindra Kamanditya

{"title":"Development of Anomalous Video Detection System using Hybrid-Features Analysis of Actions and Scene-Backgrounds Information","authors":"Bharindra Kamanditya","doi":"10.1109/CISS53076.2022.9751197","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751197","url":null,"abstract":"Detecting an anomalous event in video clips captured from a surveillance camera is an important task, especially for security system purposes. However, as the probability of such occurrence is very low, automatic detection of the anomalous event is then necessary to replace the human labor-intensive works. Researchers have developed various methods to solve this problem, however, most of the proposed methods limit their definitions of anomalous events that might be perceived as having a different meaning when it occurs in other scene backgrounds. We have developed an automatic anomalous video detection system by extracting the individual action from the video clips, followed by extracting also various scene-background characteristics related with the respective action, and represented as a Video Graph to be classified as an anomaly through a Graph Convolutional Networks. We also constructed a new database as the available databases could not be used in this experiment. Results of experiments show that the various anomalous actions videos have been successfully detected with higher recognition capability compared with that of the conventional methods.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133767685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Statistical Delay and Error-Rate Bounded QoS Control for mURLLC Over 6G Multimedia Mobile Wireless Networks in the Non-Asymptotic Regime 非渐近状态下6G多媒体移动无线网络mURLLC的统计延迟和错误率有界QoS控制

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751187

Xi Zhang, Jingqing Wang, H. Poor

{"title":"Statistical Delay and Error-Rate Bounded QoS Control for mURLLC Over 6G Multimedia Mobile Wireless Networks in the Non-Asymptotic Regime","authors":"Xi Zhang, Jingqing Wang, H. Poor","doi":"10.1109/CISS53076.2022.9751187","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751187","url":null,"abstract":"To support the exponentially increasing demand for bandwidth-intensive and delay-sensitive real-time multimedia data services, researchers have made tremendous efforts to provide a better quality-of-service (QoS) when designing next generation wireless network architecture models for massive ultra-reliable and low-latency communications (mURLLC). One of the major design issues raised by mURLLC is how to guarantee stringent delay and error-rate bounded QoS requirements when implementing short-packet data communications, such as finite blocklength coding (FBC), over highly time-varying wireless fading channels. To efficiently accommodate statistical QoS for mURLLC over 6G mobile wireless networks, it is important to remodel wireless fading channel's stochastic-characteristics by defining statistical QoS metrics and their analytical relationships, such as delay-bound-violating probability, effective capacity, error probability, outage capacity, etc., when applying FBC. However, when being integrated with FBC, how to rigorously characterize stochastic dynamics of wireless networks in terms of statistically upper-bounding both delay and error-rate QoS metrics has been neither well understood not thoroughly studied. To overcome these obstacles, in this paper we develop analytical frameworks and control mechanisms for statistical delay and error-rate bounded QoS in non-asymptotic regime. First, we establish FBC-based wireless-fading channels model by characterizing various information-theoretic specifications. Then, we develop a set of new statistical delay and error-rate bounded QoS metrics, tradeoff-functions, and control mechanisms including e-effective capacity, delay-bound-violating probability, Markov-model-based QoS-exponents functions, and FBC-based outage-capacity in finite blocklength regime. Finally, our simulation results validate and evaluate our developed mechanisms for statistical QoS in supporting mURLLC over 6G wireless networks.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125748560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Hidden Vulnerabilities in Cosine Similarity based Poisoning Defense 基于余弦相似度的投毒防御中的隐藏漏洞

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751167

Harsh Kasyap, S. Tripathy

{"title":"Hidden Vulnerabilities in Cosine Similarity based Poisoning Defense","authors":"Harsh Kasyap, S. Tripathy","doi":"10.1109/CISS53076.2022.9751167","DOIUrl":"https://doi.org/10.1109/CISS53076.2022.9751167","url":null,"abstract":"Federated learning is a collaborative learning paradigm that deploys the model to the edge for training over the local data of the participants under the supervision of a trusted server. Despite the fact that this paradigm guarantees privacy, it is vulnerable to poisoning. Malicious participants alter their locally maintained data or model to publish an insidious update, to reduce the accuracy of the global model. Recent byzantine-robust (euclidean or cosine-similarity) based aggregation techniques, claim to protect against data poisoning attacks. On the other hand, model poisoning attacks are more insidious and adaptable to current defenses. Though different local model poisoning attacks are proposed to attack euclidean based defenses, we could not find any work to investigate cosine-similarity based defenses. We examine such defenses (FLTrust and FoolsGold) and find their underlying issues. We also demonstrate an efficient layer replacement attack that is adaptable to FLTrust, impacting to lower the accuracy up to 10%. Further, we propose a cosine-similarity based local model poisoning attack (CSA) on FLTrust and FoolsGold, which generates diverse and poisonous client updates. The later attack maintains a high trust score and a high averaged weighted score for respective defenses. Experiments are carried out on different datasets, with varying attack capabilities and settings, to study the effectiveness of the proposed attack. The results show that the test loss is increased by 10 - 20×.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129582416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Product Market Demand Analysis Using NLP in Banglish Text with Sentiment Analysis and Named Entity Recognition 基于情感分析和命名实体识别的孟加拉语文本产品市场需求分析

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.48550/arXiv.2204.01827

Md. Sabbir Hossain, Nishat Nayla, Annajiat Alim Rasel

{"title":"Product Market Demand Analysis Using NLP in Banglish Text with Sentiment Analysis and Named Entity Recognition","authors":"Md. Sabbir Hossain, Nishat Nayla, Annajiat Alim Rasel","doi":"10.48550/arXiv.2204.01827","DOIUrl":"https://doi.org/10.48550/arXiv.2204.01827","url":null,"abstract":"Product market demand analysis plays a significant role for originating business strategies due to its noticeable impact on the competitive business field. Furthermore, there are roughly 228 million native Bengali speakers, the majority of whom use Banglish text to interact with one another on social media. Consumers are buying and evaluating items on social media with Banglish text as social media emerges as an online marketplace for entrepreneurs. People use social media to find preferred smartphone brands and models by sharing their positive and bad experiences with them. For this reason, our goal is to gather Banglish text data and use sentiment analysis and named entity identification to assess Bangladeshi market demand for smartphones in order to determine the most popular smartphones by gender. We scraped product related data from social media with instant data scrapers and crawled data from Wikipedia and other sites for product information with python web scrapers. Using Python's Pandas and Seaborn libraries, the raw data is filtered using NLP methods. To train our datasets for named entity recognition, we utilized Spacey's custom NER model, Amazon Comprehend Custom NER. A tensorflow sequential model was deployed with parameter tweaking for sentiment analysis. Meanwhile, we used the Google Cloud Translation API to estimate the gender of the reviewers using the BanglaLinga library. In this article, we use natural language processing (NLP) approaches and several machine learning models to identify the most in-demand items and services in the Bangladeshi market. Our model has an accuracy of 87.99% in Spacy Custom Named Entity recognition, 95.51% in Amazon Comprehend Custom NER, and 87.02% in the Sequential model for demand analysis. After Spacy's study, we were able to manage 80% of mistakes related to misspelled words using a mix of Levenshtein distance and ratio algorithms.","PeriodicalId":305918,"journal":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122785392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Fast Breadth-First Search Approximation for Epidemic Source Inference 流行病源推断的快速宽度优先搜索近似

2022 56th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2022-03-09 DOI: 10.1109/CISS53076.2022.9751156

Congduan Li, Siya Chen, C. Tan

引用次数: 0