2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)最新文献_第3页

Message from the AITS 2022 Organizers AITS 2022主办方寄语

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00010

引用次数: 0

On the impact of non-IID data on the performance and fairness of differentially private federated learning 非iid数据对差分私有联邦学习性能和公平性的影响

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00018

Saba Amiri, Adam Belloum, Eric T. Nalisnick, S. Klous, L. Gommans

{"title":"On the impact of non-IID data on the performance and fairness of differentially private federated learning","authors":"Saba Amiri, Adam Belloum, Eric T. Nalisnick, S. Klous, L. Gommans","doi":"10.1109/dsn-w54100.2022.00018","DOIUrl":"https://doi.org/10.1109/dsn-w54100.2022.00018","url":null,"abstract":"Federated Learning enables distributed data holders to train a shared machine learning model on their collective data. It provides some measure of privacy by not requiring the data be pooled and centralized but still has been shown to be vulnerable to adversarial attacks. Differential Privacy provides rigorous guarantees and sufficient protection against adversarial attacks and has been widely employed in recent years to perform privacy preserving machine learning. One common trait in many of recent methods on federated learning and federated differentially private learning is the assumption of IID data, which in real world scenarios most certainly does not hold true. In this work, we empirically investigate the effect of non-IID data on node level on federated, differentially private, deep learning. We show the non-IID data to have a negative impact on both performance and fairness of the trained model and discuss the trade off between privacy, utility and fairness. Our results highlight the limits of common federated learning algorithms in a differentially private setting to provide robust, reliable results across underrepresented groups.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134476030","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: 5

Multi-authoritative Users Assured Data Deletion Scheme in Cloud Computing 云计算中多授权用户保证数据删除方案

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00033

Junfeng Tian, Ruxin Bai, Tianfeng Zhang

{"title":"Multi-authoritative Users Assured Data Deletion Scheme in Cloud Computing","authors":"Junfeng Tian, Ruxin Bai, Tianfeng Zhang","doi":"10.1109/dsn-w54100.2022.00033","DOIUrl":"https://doi.org/10.1109/dsn-w54100.2022.00033","url":null,"abstract":"With the rapid development of cloud storage technology, an increasing number of enterprises and users choose to store data in the cloud, which can reduce the local overhead and ensure safe storage, sharing, and deletion. In cloud storage, safe data deletion is a critical and challenging problem. This paper proposes an assured data deletion scheme based on multi-authoritative users in the semi-trusted cloud storage scenario (MAU-AD), which aims to realize the secure management of the key without introducing any trusted third party and achieve assured deletion of cloud data. MAU-AD uses access policy graphs to achieve fine-grained access control and data sharing. Besides, the data security is guaranteed by mutual restriction between authoritative users, and the system robustness is improved by multiple authoritative users jointly managing keys. In addition, the traceability of misconduct in the system can be realized by blockchain technology. Through simulation experiments and comparison with related schemes, MAU-AD is proven safe and effective, and it provides a novel application scenario for the assured deletion of cloud storage data.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114651299","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

SCUC-DSAC: A Data Sharing Access Control Model Based on Smart Contract and User Credit SCUC-DSAC:基于智能合约和用户信用的数据共享访问控制模型

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00031

Guangxia Xu, Li Wang

{"title":"SCUC-DSAC: A Data Sharing Access Control Model Based on Smart Contract and User Credit","authors":"Guangxia Xu, Li Wang","doi":"10.1109/dsn-w54100.2022.00031","DOIUrl":"https://doi.org/10.1109/dsn-w54100.2022.00031","url":null,"abstract":"In the context of today's big data era, there is an urgent need for data sharing in various industries. Traditional data sharing schemes are highly centralized and have problems such as single point of failure and data privacy leakage caused by the vulnerability of data storage systems to attackers, and there are also problems such as difficulty in determining data ownership, insufficient granularity of access control, and low transparency of data sharing process. In this paper, an access control model for data sharing based on smart contract and user credit (SCUC-DSAC) is proposed. Based on the consortium blockchain, the attribute-based access control strategy and user credit are combined to provide dynamic and fine-grained access control for users. The data in the model is encrypted and stored in the interstellar file system. The access authorization process is implemented in the smart contract to improve the transparency of the data sharing process. Theoretical and experimental analysis shows that this model meets the functional and security requirements in data sharing scenarios, and the performance of blockchain network is good.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117184755","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

Machine Learning Analysis of Memory Images for Process Characterization and Malware Detection 用于进程表征和恶意软件检测的内存图像的机器学习分析

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00035

Seth Lyles, Mark Desantis, John Donaldson, Micaela Gallegos, Hannah Nyholm, C. Taylor, Kristine Monteith

引用次数: 1

Message from the DSML 2022 Organizers 来自DSML 2022组织者的信息

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00008

引用次数: 0

Message from the SSIV 2022 Organizers 2022年国际工业博览会主办方寄语

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00007

引用次数: 0

Vulnerability Dataset Construction Methods Applied To Vulnerability Detection: A Survey 漏洞数据集构建方法在漏洞检测中的应用综述

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00032

Yuhao Lin, Ying Li, Mianxue Gu, Hongyu Sun, Qiuling Yue, Jinglu Hu, Chunjie Cao, Yuqing Zhang

{"title":"Vulnerability Dataset Construction Methods Applied To Vulnerability Detection: A Survey","authors":"Yuhao Lin, Ying Li, Mianxue Gu, Hongyu Sun, Qiuling Yue, Jinglu Hu, Chunjie Cao, Yuqing Zhang","doi":"10.1109/dsn-w54100.2022.00032","DOIUrl":"https://doi.org/10.1109/dsn-w54100.2022.00032","url":null,"abstract":"The increasing number of security vulnerabilities has become an important problem that needs to be solved urgently in the field of software security, which means that the current vulnerability mining technology still has great potential for development. However, most of the existing AI-based vulnerability detection methods focus on designing different AI models to improve the accuracy of vulnerability detection, ignoring the fundamental problems of data-driven AI-based algorithms: first, there is a lack of sufficient high-quality vulnerability data; second, there is no unified standardized construction method to meet the standardized evaluation of different vulnerability detection models. This all greatly limits security personnel’s in-depth research on vulnerabilities. In this survey, we review the current literature on building high-quality vulnerability datasets, aiming to investigate how state-of-the-art research has leveraged data mining and data processing techniques to generate vulnerability datasets to facilitate vulnerability discovery. We also identify the challenges of this new field and share our views on potential research directions.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123283583","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

Tiny Black Boxes: A nano-Drone Safety Architecture 微型黑匣子:纳米无人机安全架构

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00013

Connor Sexton, Joseph Callenes

{"title":"Tiny Black Boxes: A nano-Drone Safety Architecture","authors":"Connor Sexton, Joseph Callenes","doi":"10.1109/dsn-w54100.2022.00013","DOIUrl":"https://doi.org/10.1109/dsn-w54100.2022.00013","url":null,"abstract":"As small-form factor drones grow more intelligent, they increasingly require more sophisticated capabilities to record sensor data and system state, ensuring safe and improved operation. Already regulations for black boxes, electronic data recorders (EDRs), for determining liabilities and improving the safety of large-form factor autonomous vehicles are becoming established. Conventional techniques use hardened memory storage units that conserve all sensor (visual) and system operational state; and N-way redundant models for detecting uncertainty in system operation. For small-form factor drones, which are highly limited by weight, power, and computational resources, these techniques become increasingly prohibitive. In this paper, we propose a safety architecture for resource constrained autonomous vehicles that enables the development of safer and more efficient nano-drone systems. The insight for the proposed safety architecture is that the regular structure of data-driven models used to control drones can be exploited to efficiently compress and identify key events that should be conserved in the EDR subsystem. We describe an implementation of the architecture, including hardware and software support and quantify the benefits of the approach. We show that the proposed techniques can increase that amount of recorded flight time by over 10x and reduce energy usage by over 10x for high resolution systems.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130407023","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

Stealthy Data Corruption Attack Against Road Traffic Congestion Avoidance Applications 针对道路交通避免拥塞应用的隐形数据损坏攻击

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00011

Aawista Chaudhry, Talal Halabi, Mohammad Zulkernine

{"title":"Stealthy Data Corruption Attack Against Road Traffic Congestion Avoidance Applications","authors":"Aawista Chaudhry, Talal Halabi, Mohammad Zulkernine","doi":"10.1109/dsn-w54100.2022.00011","DOIUrl":"https://doi.org/10.1109/dsn-w54100.2022.00011","url":null,"abstract":"Intelligent Transportation Systems (ITS) leverage open and real-time sharing of traffic data to enable more efficient transportation. However, the data exchanged over the vehicular network are easily corruptible via attacks known as misbehaviours. Misbehaviour detectors have been extensively developed but remain siloed and lack consideration of advanced attacks amalgamating multiple misbehaviours. These may be carried out as part of Advanced Persistent Threats. This paper presents a new approach to specifically designing stealthy data corruption attacks within ITS, and by extension in other data-reliant Cyber-Physical Systems. A Stackelberg security game is devised to model the actions of evasive attackers targeting congestion avoidance applications. The game is then solved to produce the optimal attack and defense strategies. The new stealthy attack achieves the intended long-term impact while improving evasion performance. This research direction exploring sophisticated attacks will allow to advance the design of robust misbehavior detection systems.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130801740","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