2023 IEEE International Conference on Cyber Security and Resilience (CSR)最新文献_第9页

A Survey of Attacks and Defenses for Deep Neural Networks 深度神经网络攻击与防御综述

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224947

Daniel Machooka, Xiaohong Yuan, A. Esterline

引用次数: 0

Ransomware Detection based on Network Behavior using Machine Learning and Hidden Markov Model with Gaussian Emission 基于机器学习和高斯发射隐马尔可夫模型的网络行为勒索软件检测

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10225001

Aman Srivastava, Nitesh Kumar, Anand Handa, S. Shukla

引用次数: 0

A Taxonomic Survey of Model Extraction Attacks 模型提取攻击的分类研究

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224959

Didem Genç, Mustafa Özuysal, E. Tomur

引用次数: 1

Identification of Vulnerable IoT Enabled Transportation Infrastructure into a Cyber-Physical Transportation Network 将易受攻击的物联网交通基础设施识别为网络物理交通网络

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224993

K. Ntafloukas, L. Pasquale, Beatriz Martinez-Pastor, D. McCrum

{"title":"Identification of Vulnerable IoT Enabled Transportation Infrastructure into a Cyber-Physical Transportation Network","authors":"K. Ntafloukas, L. Pasquale, Beatriz Martinez-Pastor, D. McCrum","doi":"10.1109/CSR57506.2023.10224993","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224993","url":null,"abstract":"Vulnerability of transportation networks to cyber-physical attacks is of major concern, due to security issues of Internet of Things devices in the sensing layer of transportation infrastructure. However, traditional vulnerability approaches in the civil engineering domain, overlook the integration of physical and cyber space. In this paper, we propose a new approach to identify vulnerable Internet of Things enabled transportation infrastructure and assess the vulnerability of transportation networks. The approach relies on a Bayesian network attack graph that enables the probabilistic modeling of vulnerability states in physical and cyber space. Based on a probability indicator that considers the attacker characteristics and the control barriers we identify the vulnerable transportation infrastructure and assess the vulnerability, as a drop in transportation network efficiency. Monte Carlo simulations are performed as a method to evaluate the results of a case study transportation network. The results are of interest to stakeholders in the transportation domain and indicate the increasing susceptibility due to deficient control barriers in both spaces.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"17 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":"126157460","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

Trojan Triggers for Poisoning Unmanned Aerial Vehicles Navigation: A Deep Learning Approach 用于毒害无人机导航的木马触发器:一种深度学习方法

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224932

Mohammed Mynuddin, Sultan Uddin Khan, M. N. Mahmoud

{"title":"Trojan Triggers for Poisoning Unmanned Aerial Vehicles Navigation: A Deep Learning Approach","authors":"Mohammed Mynuddin, Sultan Uddin Khan, M. N. Mahmoud","doi":"10.1109/CSR57506.2023.10224932","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224932","url":null,"abstract":"Cybersecurity for unmanned aerial vehicles (UAVs) has recently gained much attention due to an increase in cyberattacks against drone systems. Many significant cyber security attacks on UAVs have occurred in recent years due to a lack of vulnerability assessments and inadequate security countermeasures. A Trojan attack is a type of cyberattack where Deep Neural Networks (DNN) models are poisoned by injecting malicious modifications into the original design, which leads the DNN to misclassify certain inputs after being triggered. In this paper, we investigate Trojan attacks against neural networks. For a Trojan attack, we consider the DroNet architecture. DroNet is a convolutional neural network capable of safely driving a UAV across city streets. DroNet navigates UAVs by predicting steering angles and collision probabilities from camera images. For the attacking purpose, we have generated poisonous collision and steering angle datasets for DroNet. The TrojAI software framework is used to generate poisonous datasets and Trojan models. First, the effectiveness of the Trojan attack is examined on the DroNet model using poisonous and steering angle datasets. Then, we regulate the intensity of the designed trigger and review the performance of the DroNet architecture. Finally, we proposed a trojan detection technique using label visualization for clean and poisonous datasets.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"35 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114128234","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

Enhancing Industrial Cyber-Physical Systems Security with Smart Probing Approach 用智能探测方法增强工业网络物理系统的安全性

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224912

Valeria Bonagura, Chiara Foglietta, S. Panzieri, F. Pascucci

{"title":"Enhancing Industrial Cyber-Physical Systems Security with Smart Probing Approach","authors":"Valeria Bonagura, Chiara Foglietta, S. Panzieri, F. Pascucci","doi":"10.1109/CSR57506.2023.10224912","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224912","url":null,"abstract":"Critical infrastructures and industrial facilities are examples of Cyber-Physical Systems, which are sophisticated systems that integrate physical processes and communication networks. Regrettably, the combination of physical and cyber layers raises the possibility of complications such as a larger surface area for cyberattacks. Due to the unique characteristics of the industrial environment, applying safeguarding architecture similar to that created for the IT sector is not conceivable. Yet, in this study, we exploit the features of industrial communication networks to design the Smart Security Probe, an intrusion detection system for industrial networks. This solution was created to detect potential anomalies in network traffic and to assist in inferring potential anomalies in data connected to physical processes. Smart Security Probe has two operating modes: passive and interactive. When the passive mode is selected, the proposed device analyses the traffic shape in a transparent way, while in the interactive mode it is possible to send packets to allow further analysis and the device is visible in the network. When the interactive mode is activated, a model-based anomaly detection system is included in the suggested approach. Using the Message Queuing Telemetry Transport protocol, the Smart Security Probe can communicate with a remote station to implement an asynchronous Extended Kalman Filter. Smart Security Probe was tested and validated in a system comprised of one Programmable Logic Controller and one Supervisory Control and Data Acquisition system that controls three simulated interconnected tanks.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"32 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":"124043975","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

Qerberos: A Protocol for Secure Distribution of QRNG Keys Qerberos:一个用于安全分发QRNG密钥的协议

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224969

David Soler, C. Dafonte, Francisco Nóvoa, M. Fernández-Veiga, Ana Fernández Vilas, R. P. Díaz-Redondo

引用次数: 0

Detection of Radio Frequency Interference in Satellite Ground Segments 卫星地面段射频干扰检测

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10225005

L. Coppolino, S. D'Antonio, Federica Uccello, Anastasios Lyratzis, Constantinos Bakalis, Souzana Touloumtzi, I. Papoutsis

引用次数: 0

Modelling and Analysing Security Threats Targeting Protective Relay Operations in Digital Substations 数字化变电站继电保护运行安全威胁建模与分析

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224964

Mohamed Faisal Elrawy, L. Hadjidemetriou, C. Laoudias, M. Michael

{"title":"Modelling and Analysing Security Threats Targeting Protective Relay Operations in Digital Substations","authors":"Mohamed Faisal Elrawy, L. Hadjidemetriou, C. Laoudias, M. Michael","doi":"10.1109/CSR57506.2023.10224964","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224964","url":null,"abstract":"Digitalization of power substations is mandatory to increase the efficiency, stability and reliability of smart grids. In digital substations, protective relays (e.g., overcurrent relays) can communicate using the IEC 61850 GOOSE protocol to provide fast response and discrimination capabilities to clear and isolate grid faults (e.g., short circuit events). However, exploitation of the GOOSE protocol vulnerabilities by cyber- attackers may lead to catastrophic failures in power substation equipment. Recent works consider the security vulnerabilities of the GOOSE protocol. However, a holistic approach to study different attack techniques and strategies that can be used by cyber-attackers to hijack communication channels between relays is currently missing. For example, the timing of injecting attack and the operation mode of the protective relay during the attack could lead to different impact. Moreover, a masquerade attack, mimicking the GOOSE protocol behaviour, is harder to be detected. This paper presents a comprehensive study of attack techniques and strategies and their respective impact, utilizing an integrated simulation model of the protective relays and their physical, communication and cybersecurity operations in a digital substation. Moreover, an assessment method for cyber-attacks is proposed based on the impact and the warnings caused by these attacks. Six simulation scenarios are modelled and analyzed, demonstrating the applicability of the proposed method.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"23 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":"132470668","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

Minimizing Software-Rooted Risk through Library Implementation Selection 通过库实现选择最小化软件根源风险

2023 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2023-07-31 DOI: 10.1109/CSR57506.2023.10224931

P. Sotiropoulos, Christos-Minas Mathas, C. Vassilakis, N. Kolokotronis

{"title":"Minimizing Software-Rooted Risk through Library Implementation Selection","authors":"P. Sotiropoulos, Christos-Minas Mathas, C. Vassilakis, N. Kolokotronis","doi":"10.1109/CSR57506.2023.10224931","DOIUrl":"https://doi.org/10.1109/CSR57506.2023.10224931","url":null,"abstract":"In contemporary Internet of Things (IoT) systems, complex software artifacts are deployed to realize the required functionalities. The business logic of these software artifacts is uniquely composed through code that is customly developed according to the requirements, while all software artifacts utilize libraries that implement generic functionalities, which are needed in the context of the realized operations. Libraries, however, often entail vulnerabilities, which may be exploited by threat agents to attack the system. In many cases, the functionality required by an application is realized by a number of alternative libraries, with each library having its own list of vulnerabilities, while differentiations in other non-functional properties (e.g. execution efficiency, memory footprint etc.) may also be present. In this paper, we present an approach for automating the task of minimizing the risk level of IoT systems that is owing to the vulnerabilities of libraries required by software artifacts. The proposed approach exploits knowledge on which libraries provide equivalent implementations of the same functionalities, and automatically assesses the risk level of candidate library combinations and finally selects the library configuration exhibiting the minimum risk level to bundle into the executable software artifact. Additionally, the risk level of candidate implementations is constantly monitored for new vulnerability identifications or fixes in the implementations, triggering new risk assessments and producing new executables as appropriate. The proposed approach can be used in IoT platform deployment to minimize the software-rooted risk level.","PeriodicalId":354918,"journal":{"name":"2023 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"39 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":"132020304","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