2023 IEEE International Conference on Cyber Security and Resilience (CSR)最新文献

Area-Delay Efficient Security Scheme for Smart Hospital Systems 智能医院系统的区域延迟高效安全方案

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224966

Kyriaki Tsantikidou, Dimitrios Boufeas, N. Sklavos

{"title":"Area-Delay Efficient Security Scheme for Smart Hospital Systems","authors":"Kyriaki Tsantikidou, Dimitrios Boufeas, N. Sklavos","doi":"10.1109/CSR57506.2023.10224966","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224966","url":null,"abstract":"In recent years, traditional Hospital facilities are adopting new technologies. Smart Hospitals mostly utilize the Internet of Things (loT) technology due to its vast capabilities in connectivity. This loT network requires specific protocols for proper functionality. Message Queuing Telemetry Transport (MQTT) protocol is suitable for managing the communication and routing procedures of the resource constrained loT environment. Nevertheless, both MQTT and loT have various vulnerabilities and threats that must first be addressed. In this paper, a lightweight key management procedure is analyzed, an end-to-end payload encryption method is followed, and a processor with different cryptographic mechanisms is implemented. This combination of processes best complements the E-Health-based Hospital architecture, requiring minimum resources and complete security. The proposed crypto processor efficiently implements three different cryptographic primitives in a RISC- V architecture, providing flexibility. It achieves the best area-delay compared to other hardware-based security schemes, with 61.3% resource reduction and minimum added computation overhead. This is accomplished due to proper formatting of specific instructions and a function, operation and register sharing methodology.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125115398","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

Privacy-preserving Federated Learning System for Fatigue Detection 保护隐私的疲劳检测联邦学习系统

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224953

Mohammadreza Mohammadi, R. Allocca, David Eklund, Rakesh Shrestha, Sima Sinaei

{"title":"Privacy-preserving Federated Learning System for Fatigue Detection","authors":"Mohammadreza Mohammadi, R. Allocca, David Eklund, Rakesh Shrestha, Sima Sinaei","doi":"10.1109/CSR57506.2023.10224953","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224953","url":null,"abstract":"Context:. Drowsiness affects the driver's cognitive abilities, which are all important for safe driving. Fatigue detection is a critical technique to avoid traffic accidents. Data sharing among vehicles can be used to optimize fatigue detection models and ensure driving safety. However, data privacy issues hinder the sharing process. To tackle these challenges, we propose a Federated Learning (FL) approach for fatigue-driving behavior monitoring. However, in the FL system, the privacy information of the drivers might be leaked. In this paper, we propose to combine the concept of differential privacy (DP) with Federated Learning for the fatigue detection application, in which artificial noise is added to parameters at the drivers' side before aggregating. This approach will ensure the privacy of drivers' data and the convergence of the federated learning algorithms. In this paper, the privacy level in the system is determined in order to achieve a balance between the noise scale and the model's accuracy. In addition, we have evaluated our models resistance against a model inversion attack. The effectiveness of the attack is measured by the Mean Squared Error (MSE) between the reconstructed data point and the training data. The proposed approach, compared to the non-DP case, has a 6% accuracy loss while decreasing the effectiveness of the attacks by increasing the MSE from 5.0 to 7.0, so a balance between accuracy and noise scale is achieved.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128186558","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

An Explainable Artificial Intelligence Approach for a Trustworthy Spam Detection 一种可解释的可信赖的垃圾邮件检测人工智能方法

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224956

A. Ibrahim, M. Mejri, Fehmi Jaafar

{"title":"An Explainable Artificial Intelligence Approach for a Trustworthy Spam Detection","authors":"A. Ibrahim, M. Mejri, Fehmi Jaafar","doi":"10.1109/CSR57506.2023.10224956","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224956","url":null,"abstract":"For decades, spam emails have been one of the most serious and irritating cybersecurity threats. For detecting spam emails, a variety of machine learning (ML) and deep learning (DL) approaches are used. These approaches identify spam emails in the inbox and send them to a junk folder. However, these approaches have some limitations, such as their inability to explain why an email is considered spam. The current paper introduces the X_SPAM approach by combining the machine learning technique (Random Forest) and deep learning technique (LSTM) to detect spam and uses the Explainable Artificial Intelligence technique (LIME) to increase the trustworthiness of spam detection by explaining the reason for their classification. We evaluate the proposed approach using two different datasets (LING without metadata and Enron with metadata). We found that the proposed approach has achieved a high accuracy rate for RF and LSTM at 98.13% and 99.13% respectively. Moreover, the study exhibits a visualizing manner to eliminate the black box drawback for ML and DL classifiers to increase the approach's trustworthiness.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131706351","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

Proactive Measures for Cyber-Physical Systems Cybersecurity 网络物理系统网络安全的主动措施

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224929

Kamal Taha

{"title":"Proactive Measures for Cyber-Physical Systems Cybersecurity","authors":"Kamal Taha","doi":"10.1109/CSR57506.2023.10224929","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224929","url":null,"abstract":"Reactive security measures for cyber-physical systems (CPS) are ineffective. It is imperative for replacing these measures with proactive ones for the sustainability of the CPS cybersecurity. We introduce a novel proactive methodology for CPS cybersecurity. We implemented this methodology in a system called CPM-CPS. The methodology is summarized as follows: (a) clustering the CPS devices with LAN-based network sharing, (b) identifying the influential devices in each cluster, and (c) identifying the central devices at the WAN level that have network sharing with the influential devices in the different clusters. The file sharing of the identified influential devices at both LAN and WAN levels needs to be paid more attention to. Such measures can help in detecting potential security risks and preventing cyber-attacks against these influential devices before they share their infected files with other devices. Security equipment like intrusion detection systems can be provided to these influential devices. We introduce in this paper novel k-clique-based modeling techniques for clustering LAN devices. We introduce novel techniques for identifying LAN and WAN influential devices using coefficient-based and Independent Cascades-based modeling techniques. We experimentally evaluated our system CPM-CPS and compared it with four methods. Results showed marked improvement.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122158819","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

The Alliance of HE and TEE to Enhance their Performance and Security 高等教育学院与TEE的联盟，以提高其性能和安全性

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224999

S. D'Antonio, Giannis Lazarou, Giovanni Mazzeo, Oana Stan, Martin Zuber, Ioannis Tsavdaridis

{"title":"The Alliance of HE and TEE to Enhance their Performance and Security","authors":"S. D'Antonio, Giannis Lazarou, Giovanni Mazzeo, Oana Stan, Martin Zuber, Ioannis Tsavdaridis","doi":"10.1109/CSR57506.2023.10224999","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224999","url":null,"abstract":"While protection of data at-rest and data in-transit can be achieved using standard algorithms and technologies, the protection of data in-use is still, to a large extent, an open issue. Homomorphic Encryption (HE) and Trusted Execution Environment (TEE) are among the most popular approaches to shield computations. The former ensures high security guarantees but it suffers from a significant overhead. The latter, instead, provides lower execution time but it is affected by security drawbacks. In this paper, we propose SOTERIA, a privacy-preserving computation solution that combines HE and TEE to mitigate their limitations. The approach foresees the execution of sensitive processing with homomorphic encryption and the usage of a TEE to perform switches between different homomorphic cryptosystems. In fact, there are different kinds of computation algorithms where the co-existence of linear and non-linear functions makes the HE-based processing even more onerous. SOTERIA is developed in the context of the ENCRYPT project and will be validated in a use case of financial data processing.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126142599","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

Exposed: Critical Vulnerabilities in USSD Banking Authentication Protocols 暴露:美元银行认证协议中的关键漏洞

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224933

Zaynab Lamoyero, Oluwatobi Fajana

{"title":"Exposed: Critical Vulnerabilities in USSD Banking Authentication Protocols","authors":"Zaynab Lamoyero, Oluwatobi Fajana","doi":"10.1109/CSR57506.2023.10224933","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224933","url":null,"abstract":"Unstructured Supplementary Service Data (USSD) authentication has been widely adopted as a popular method for verifying user identity and securing transactions in mobile financial banking, particularly in Sub-Saharan African countries. This is due to the convenience, speed, and accessibility since they do not require high-powered computing phones, large storage, or internet connectivity. However, like every technological advancement, this has been widely exploited by malicious actors due to weak authentication requirements. This study critically examines all 19 commercial banks in Nigeria, which has the largest USSD banking usage in Sub-Saharan Africa. We analyse 30 scenarios to conduct an anatomy and build a timeline of USSD banking attacks. Furthermore, we critically but anonymously examine each USSD banking platform against several security factors selected from government guidelines, the National Institute of Standards (NIST) SP800-63B framework and the National Cyber Security Centre (NCSC) recommendations. This led to the revelation that certain services only require a single authentication, such as PIN, while others require no authentication at all. Also, most of the banks failed to comply with governmental and industrial authentication standards. Furthermore, we present a 5-phase timeline of USSD attacks and address present recommendations for different stakeholders at the various stages.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125029734","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

Understanding Human Factors of Cybersecurity: Drivers of Insider Threats 理解网络安全的人为因素:内部威胁的驱动因素

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224926

Marcus L. Green, Priya D. Dozier

引用次数: 0

Practical Multi-Key Homomorphic Encryption for More Flexible and Efficient Secure Federated Average Aggregation 实用的多密钥同态加密，实现更灵活高效的安全联邦平均聚合

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224979

A. Pedrouzo-Ulloa, Aymen Boudguiga, Olive Chakraborty, Renaud Sirdey, Oana Stan, Martin Zuber

引用次数: 0

To TTP or not to TTP?: Exploiting TTPs to Improve ML-based Malware Detection TTP还是不TTP?:利用ttp改进基于ml的恶意软件检测

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10225000

Yashovardhan Sharma, Eleonora Giunchiglia, S. Birnbach, I. Martinovic

引用次数: 1

A Driver Detection Method by Means of Explainable Deep Learning 基于可解释深度学习的驾驶员检测方法

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224913

Fabio Martinelli, F. Mercaldo, A. Santone

引用次数: 0