Proceedings of the ACM Turing Award Celebration Conference - China最新文献

筛选
英文 中文
Lossless Database Watermarking Based on Order-preserving Encryption 基于保序加密的数据库无损水印
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3474075
S. Yan, Shuli Zheng, Baohong Ling, Donghui Hu
{"title":"Lossless Database Watermarking Based on Order-preserving Encryption","authors":"S. Yan, Shuli Zheng, Baohong Ling, Donghui Hu","doi":"10.1145/3472634.3474075","DOIUrl":"https://doi.org/10.1145/3472634.3474075","url":null,"abstract":"With the development of information technology and the popularity of Internet applications, the database outsourcing service is gaining popularity. However, since the database services provided by third parties are not completely trusted, the outsourced database model has to face a series of security issues such as privacy leakage, data theft, malicious tampering, and so forth. To both provide privacy protection and copyright tracking, this paper proposes a lossless database watermarking method based on order-preserving encryption. In the proposed method, the data owner encrypts the original data using order-preserving encryption algorithms. The outsourced database administrator then embeds the watermark bits by modifying the parities of the cover encrypted attribute values. At the database client, the database user extracts the embedded watermark bits based on the majority voting mechanism. The original database is recovered by directly decrypting the marked encrypted database. The experimental results and analysis show that the proposed method has the advantages of lossless, strong robustness, high embedding rate, no auxiliary message and low computational complexity.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122582818","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: 4
Multiple color medical images zero-watermark scheme based on quaternion generalized Fourier descriptor and QR code 基于四元数广义傅里叶描述子和QR码的多色医学图像零水印方案
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3474079
Baowei Wang, Weishen Wang, Peng Zhao
{"title":"Multiple color medical images zero-watermark scheme based on quaternion generalized Fourier descriptor and QR code","authors":"Baowei Wang, Weishen Wang, Peng Zhao","doi":"10.1145/3472634.3474079","DOIUrl":"https://doi.org/10.1145/3472634.3474079","url":null,"abstract":"Most of the existing zero-watermark algorithms for medical images are only applicable to grayscale images, and when they protect the copyright of a large number of medical images, the repetitive operation will bring a lot of time and storage costs. Therefore, to solve the above problems, this paper proposes a zero-watermark scheme for multiple color medical images based on quaternion generalized Fourier descriptor(QGFD) and QR code. QGFD is used to calculate the feature invariants of each color medical image, then the representative features of each image are selected to form the feature matrix, and binarize it to get the binary feature image, finally, the zero-watermark image can be obtained by performing an XOR operation on the scrambled copyright image and feature image. The experimental results show that the proposed scheme can not only effectively resist common attacks, geometric attacks and joint attacks, but also can effectively reduce the time and storage cost of copyright protection for a large number of medical images.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121311175","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: 1
Multi-domain Reversible Data Hiding in JPEG Images 多域可逆数据隐藏在JPEG图像
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3474078
Wanli Lv, Hongnian Guo, Yang Du, Jinmin Hu, Z. Yin
{"title":"Multi-domain Reversible Data Hiding in JPEG Images","authors":"Wanli Lv, Hongnian Guo, Yang Du, Jinmin Hu, Z. Yin","doi":"10.1145/3472634.3474078","DOIUrl":"https://doi.org/10.1145/3472634.3474078","url":null,"abstract":"Images reversible data hiding is a technique to embed additional data by modifying carrier images in a recoverable way, that has attracted more and more attention, especially for the most widely used JPEG format. As data carrier or modification domain, researchers usually choose one of two, DCT coefficients or entropy-coded data, that may result in different image filesize expansion or visual quality distortion. To this end, a new reversible data hiding method for JPEG images in multi-domain is proposed. Unlike existing methods, both of DCT coefficients and entropy-coded data can be used to embed data at the same time. In order to make trade-off between distortion of DCT coefficients domain and entropy-coded data domain, a reasonable payload distribution algorithm is also proposed. Experimental results demonstrate the superior to state-of-the-art works.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114071422","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
A Passenger Flow Transfer Prediction Model for Collinear Stations Based on Connection Model of New Station 基于新车站连接模型的共线车站客流转移预测模型
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3472651
Wenlong Yu, Huizhen Zhang, Jiawei Pan
{"title":"A Passenger Flow Transfer Prediction Model for Collinear Stations Based on Connection Model of New Station","authors":"Wenlong Yu, Huizhen Zhang, Jiawei Pan","doi":"10.1145/3472634.3472651","DOIUrl":"https://doi.org/10.1145/3472634.3472651","url":null,"abstract":"In order to solve the problem that the subway attracts less passenger flow, there are too many overlapping lines between the bus and the subway, resulting in traffic congestion of other conventional bus lines along the subway. For this reason, we take Xiamen as the sample point, and consider the number of subway stations and the length of subway bus configuration. The mathematical model of matching bus line density and traffic line length is referred. Based on the accessibility analysis, a new bus connecting station model with more than five stations on the same line is designed. We propose two models for the alignment adjustment of the number of common stations of subway and public transport. It is shown that the average connecting time from bus to subway is reduced by 15.58 minutes, and the passenger flow attracted by subway is increased by 2.15%-19.99%, compared with the unadjusted road network layout.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130739759","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
BSLKT: A Bagging Model with Self-Attention and LightGBM for Knowledge Tracing BSLKT:一种具有自关注和LightGBM的知识追踪Bagging模型
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3472664
Zhuo Zhang, Haoyun Li
{"title":"BSLKT: A Bagging Model with Self-Attention and LightGBM for Knowledge Tracing","authors":"Zhuo Zhang, Haoyun Li","doi":"10.1145/3472634.3472664","DOIUrl":"https://doi.org/10.1145/3472634.3472664","url":null,"abstract":"Knowledge tracing(KT) is a hot topic in computer-supported education. It’s a task that can model a sequences of learning activities that students engage with, so as to trace the students’ continuously developing state of knowledge. One important purpose of knowledge tracing is that it can evaluate students’ mastery of knowledge concepts(KCs) according to their performance in learning activities, in order to customize personalized learning plans for students to help them get better learning plans. In recent years, many knowledge tracing methods have been proposed, which can be divided into Recurrent Neural Networks(RNN) based methods and self-attention based methods. Methods based on RNN include Deep Knowledge Tracing(DKT), Dynamic Key-Value Memory Network(DKVMN), etc. These RNN methods have better performance than traditional knowledge tracing methods. However, they are not suitable for dealing with sparse data, that is, situations where students interact with few KCs. The Self-Attention model for Knowledge Tracing(SAKT) uses the self-attention mechanism, which can identify the KCs from the learning activities that students participated in and are related to a given KC, so as to predict the mastery of the given KC. Therefore, SAKT can deal with the sparse data problem that the RNN methods are not suitable for processing. LightGBM is a gradient boosting framework that uses a tree based learning algorithm and is one of the current mainstream machine learning algorithms. In order to make the prediction more accurate, we propose the BSLKT model, which fuses the SAKT model and the LightGBM model in bagging manner. In addition, we performed feature engineering preprocessing on the experiment dataset. The experiment compared the accuracy of SAKT model, LightGBM model and the BSLKT model and the results show that BSLKT can achieve better prediction performance.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127386075","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
Trusted-DNN: A TrustZone-based Adaptive Isolation Strategy for Deep Neural Networks Trusted-DNN:基于trustzone的深度神经网络自适应隔离策略
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3472652
Zhuang Liu, Ye Lu, Xueshuo Xie, Yaozheng Fang, Zhaolong Jian, Tao Li
{"title":"Trusted-DNN: A TrustZone-based Adaptive Isolation Strategy for Deep Neural Networks","authors":"Zhuang Liu, Ye Lu, Xueshuo Xie, Yaozheng Fang, Zhaolong Jian, Tao Li","doi":"10.1145/3472634.3472652","DOIUrl":"https://doi.org/10.1145/3472634.3472652","url":null,"abstract":"Deep neural network (DNN) models have been widely deployed on embedded and mobile devices in lots of application fields such as health care, face recognition, driver assistance, etc. These applications usually require privacy or trusted computing protection. However, diverse hardware resources, various transport protocols, and limited computation and storage capacity make it challenging for traditional embedded systems to provide complex security protection mechanism oriented DNN models. To meet the challenges, we propose Trusted-DNN, a TrustZone-based adaptive isolation strategy for DNN models. We first design a normal pattern to exploit TrustZone technology to provide overall protection for running DNNs. To deploy arbitrary DNN models into TrustZone, we then develop a dynamic model partition method, which makes our strategy easily adaptive to various DNN models and devices. Finally, we employ several optimization techniques to reduce the inference latency of Trusted-DNN models. We perform AlexNet on OP-TEE, which is a TrustZone-based secure operating system, based on a Raspberry Pi 3B+ board. The extensive experimental results highlight that the optimized Trusted-DNN can reduce memory footprint by up to 98% compared with the ordinary program and Trusted-DNN only increase inference latency by 22.8%. Our code is available at https://gitee.com/PaintZero/alexnet-tee.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117236691","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: 9
Recognition Of Learners’ Personality Traits For Software Engineering Education 软件工程教育中学习者人格特征的识别
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3472636
Bin Xu, Qiaoqiao Zhang, Kening Gao, Ge Yu, Zhaowu Zhang, Yidi Du
{"title":"Recognition Of Learners’ Personality Traits For Software Engineering Education","authors":"Bin Xu, Qiaoqiao Zhang, Kening Gao, Ge Yu, Zhaowu Zhang, Yidi Du","doi":"10.1145/3472634.3472636","DOIUrl":"https://doi.org/10.1145/3472634.3472636","url":null,"abstract":"It is vital for educators to teach learners in accordance with their aptitude, which can be useful to help learners reach their full potential. Educators have been taking the Myers-Briggs Type Indicator (MBTI) as a powerful tool to understand the differences in students’ learning styles, adopting appropriate teaching strategies to accommodate the learning styles of different types of students can effectively prevent students from being tired of studying. It is a problem worthy of research to recognize the students’ personality traits with technological means. Therefore, we propose a method to recognize learners’ MBTI from videos, which can be applied in the course learning and practice stages of software engineering education. We propose a novel approach to recognize the MBTI personality traits of learners from videos. Personality and emotion unconsciously affect facial expression, the speaking style in social contexts. However, in the current literature, there is no publicly available source of images dataset labeled with the MBTI personality scale; nearly all the available data are text. In this paper, we use two datasets: images extracted from ChaLearn First Impressions dataset and the Myer-Briggs Personality Type Dataset from Kaggle for our training tasks. Furthermore, we take plentiful text data labeled with the MBTI personality scale as the source domain and image data as the target domain for borrowing knowledge from the source domain to facilitate the learning task in a target domain. By adopting feature transfer, a bridge is built between the source domain and the target domain. We perform experiments on the transfer task and evaluate the effectiveness of this approach, the results of this study can assist educators in regards to the identification of learners’ MBTI personality types in a new way.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127835790","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
Exploiting Temperature-Varied Voltage Fingerprints for In-vehicle CAN Intrusion Detection
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3472662
Dong Li, Miaoqing Tian, Ruobing Jiang, Ke Yang
{"title":"Exploiting Temperature-Varied Voltage Fingerprints for In-vehicle CAN Intrusion Detection","authors":"Dong Li, Miaoqing Tian, Ruobing Jiang, Ke Yang","doi":"10.1145/3472634.3472662","DOIUrl":"https://doi.org/10.1145/3472634.3472662","url":null,"abstract":"The Controller Area Network (CAN) is the most commonly used in-vehicle protocol for reliable communication between Electronic Control Units (ECUs). Due to its broadcast nature and absence of message authentication mechanisms, CAN bus is vulnerable to several severe attacks. To combat these defects, many intrusion detection systems (IDSs) that exploit ECU’s inimitable voltage signal have been proposed. However, existing works ignore the impact of temperature changes or only consider a small range of temperature changes. Through experiences, we found that the ECU’s voltage signals will be affected by the temperature, which will cause the state-of-the-art voltage-based IDS to fail. To mitigate this deficiency, we propose a temperature-varied voltage fingerprinting scheme(TVV). TVV collects the voltage signals sent by each ECU at different temperatures, and it constructs a fingerprint database of each ECU. Then TVV performs intrusion detection based on the fingerprint database and the current driving state of the car. We have implemented TVV on both CAN bus prototype and real vehicles at a temperature of 0℃ to 80℃, and results show that our scheme is able to detect the masquerade attack.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125304169","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: 3
Cross-chain Workflow Model Based on Trusted Relay 基于可信中继的跨链工作流模型
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3472648
Xianzhe Wu
{"title":"Cross-chain Workflow Model Based on Trusted Relay","authors":"Xianzhe Wu","doi":"10.1145/3472634.3472648","DOIUrl":"https://doi.org/10.1145/3472634.3472648","url":null,"abstract":"The development of blockchain technology has led to the emergence of a large number of blockchain systems for different domains. These blockchain systems present the problem of data isolation. Chain interoperability technology, that is, cross-chain technology focuses on how to achieve value transfer and data interaction among different blockchains. However, the structural difference among the architectures of existing mainstream cross-chain solutions has brought three challenges to the cross-chain technology: the feasibility of cross-chain transactions, the structuring and standardization of cross-chain processes and the provenance of cross-chain processes. To address the above challenges, we present a Cross-chain Workflow Model. This model is based on the relay blockchain scheme, using blockchain of blockchains to make cross-chain transactions feasible. In this model, the cross-chain process is defined as a cross-chain workflow. The model takes the relaychain as the center to achieve the management of the cross-chain workflows. Experiments prove that the additional overhead caused by this model is acceptable. And this model can provide efficient cross-chain lineage query.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122775504","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: 3
Reliable and Secure Data Sharing in Decentralized Mobile Crowd Systems 分散移动人群系统中可靠安全的数据共享
Proceedings of the ACM Turing Award Celebration Conference - China Pub Date : 2021-07-30 DOI: 10.1145/3472634.3472638
Zhenni Feng, Junchang Chen, Fanbo Xu
{"title":"Reliable and Secure Data Sharing in Decentralized Mobile Crowd Systems","authors":"Zhenni Feng, Junchang Chen, Fanbo Xu","doi":"10.1145/3472634.3472638","DOIUrl":"https://doi.org/10.1145/3472634.3472638","url":null,"abstract":"Mobile crowd sensing (MCS) systems, which offer a great opportunity to fully take advantage of wisdom of the crowd, naturally benefits from low deployment cost and widely spatial coverage. Due to failure or risk caused by a central server, we study the problem of constructing an efficient mobile crowd sensing system with untrustworthy participants in a decentralized manner. We propose an efficient and practical decentralized MCS system based on a distributed auction process and the blockchain system. The proposed method achieves the optimal social profit iteratively satisfying individual rationality and protecting their privacy, through a neutral, public and trustful platform. Both theoretical analysis and numerical experiment show the effectiveness of the proposed approach.","PeriodicalId":112113,"journal":{"name":"Proceedings of the ACM Turing Award Celebration Conference - China","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131167839","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书