Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187263
M. Gromov, David Arnold, J. Saniie
Computer vision has proven itself capable of accurately detecting and classifying objects within images. This also works in cases where images are used as a way of representing data, without being actual photographs. In cybersecurity, computer vision is rarely used, however it has been used to detect botnets successfully. We applied computer vision to determine how well it would be able to detect and classify a large number of attacks and determined that it would be able to run at a decent rate on a Jetson Nano. This was accomplished by training a convolutional neural network using data publicly available in the IoT-23 database, which contains packet captures of IoT devices with and without different malware infections. The neural network was evaluated on an RTX 3050 and a Jetson Nano to see if it could be used in IoT.
{"title":"Utilizing Computer Vision Algorithms to Detect and Classify Cyberattacks in IoT Environments in Real-Time","authors":"M. Gromov, David Arnold, J. Saniie","doi":"10.1109/eIT57321.2023.10187263","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187263","url":null,"abstract":"Computer vision has proven itself capable of accurately detecting and classifying objects within images. This also works in cases where images are used as a way of representing data, without being actual photographs. In cybersecurity, computer vision is rarely used, however it has been used to detect botnets successfully. We applied computer vision to determine how well it would be able to detect and classify a large number of attacks and determined that it would be able to run at a decent rate on a Jetson Nano. This was accomplished by training a convolutional neural network using data publicly available in the IoT-23 database, which contains packet captures of IoT devices with and without different malware infections. The neural network was evaluated on an RTX 3050 and a Jetson Nano to see if it could be used in IoT.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133326894","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187259
Nicholas Ferry, Kishwar Ahmed, S. Tasnim
Recent nanotechnology advances have catalyzed sev-eral different types of engineered nanomaterials (ENMs). The nanomaterial classification interprets to identifying any particle that is smaller than hundred nanometer. Protein corona (PC) is an agglomeration of proteins that form on an ENM in organic fluids. Machine learning techniques can be useful to predict the PC formation and interaction within an ENM. In this paper, we develop a random forest model for PC formation prediction on ENMs. Further, we leverage the deep neural network (DNN) technique to accurately and efficiently predict PC formation. We also present an architecture optimization of the trained DNN model to create practically instantaneous inferences. We preform simulation study to show effectiveness of our proposed model. Experiments show that the DNN model can achieve 83.81% accuracy in PC classification on ENMs, while can significantly improve the classification performance.
{"title":"Protein Corona Formation Prediction on Engineered Nanomaterials","authors":"Nicholas Ferry, Kishwar Ahmed, S. Tasnim","doi":"10.1109/eIT57321.2023.10187259","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187259","url":null,"abstract":"Recent nanotechnology advances have catalyzed sev-eral different types of engineered nanomaterials (ENMs). The nanomaterial classification interprets to identifying any particle that is smaller than hundred nanometer. Protein corona (PC) is an agglomeration of proteins that form on an ENM in organic fluids. Machine learning techniques can be useful to predict the PC formation and interaction within an ENM. In this paper, we develop a random forest model for PC formation prediction on ENMs. Further, we leverage the deep neural network (DNN) technique to accurately and efficiently predict PC formation. We also present an architecture optimization of the trained DNN model to create practically instantaneous inferences. We preform simulation study to show effectiveness of our proposed model. Experiments show that the DNN model can achieve 83.81% accuracy in PC classification on ENMs, while can significantly improve the classification performance.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134151338","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187355
M. Chowdhury, Nafiz Rifat, M. Ahsan, Shadman Latif, Rahul Gomes, Md Saifur Rahman
The AI revolution has brought significant changes to society. AI-powered systems can analyze enormous amounts of data to optimize processes, improve accuracy, and cut costs. Nevertheless, addressing potential hazards and ethical issues related to AI enabled technologies, such as bias and job displacement, is essential. This paper presented an example of an AI revolution threatening cyber security, the ChatGPT. ChatGPT, a chatbot, can generate essays or code on demand. However, ChatGPT's security system can be circumvented or deceived to generate malicious content. Moreover, these AI enabled tools to have design issues, e.g., accuracy issues. As a result, ChatGPT can be accused of violating the confidentiality of information (privacy invasion), producing inaccurate information, and potentially facilitating attack tool generation that can compromise the availability principle of the CIA triad. This paper presents ChatGPT as a threat against the CIA triad principle by focusing on violating these principles.
{"title":"ChatGPT: A Threat Against the CIA Triad of Cyber Security","authors":"M. Chowdhury, Nafiz Rifat, M. Ahsan, Shadman Latif, Rahul Gomes, Md Saifur Rahman","doi":"10.1109/eIT57321.2023.10187355","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187355","url":null,"abstract":"The AI revolution has brought significant changes to society. AI-powered systems can analyze enormous amounts of data to optimize processes, improve accuracy, and cut costs. Nevertheless, addressing potential hazards and ethical issues related to AI enabled technologies, such as bias and job displacement, is essential. This paper presented an example of an AI revolution threatening cyber security, the ChatGPT. ChatGPT, a chatbot, can generate essays or code on demand. However, ChatGPT's security system can be circumvented or deceived to generate malicious content. Moreover, these AI enabled tools to have design issues, e.g., accuracy issues. As a result, ChatGPT can be accused of violating the confidentiality of information (privacy invasion), producing inaccurate information, and potentially facilitating attack tool generation that can compromise the availability principle of the CIA triad. This paper presents ChatGPT as a threat against the CIA triad principle by focusing on violating these principles.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114226214","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187281
M. Rakotondraibé, Tianyang Fang, J. Saniie
According to WHO's report from 2021, Drowning is the 3rd leading cause of unintentional death worldwide. The use of autonomous drones for drowning recognition can increase the survival rate and help lifeguards and rescuers with their life saving mission. This paper presents a real-time drowning recognition model and algorithm for ocean surveillance that can be implemented on a drone. The presented model has been trained using two different approaches and has 88% accuracy. Compared to the contemporary models of drowning recognition designed for swimming pools, the model presented is better suited for outdoor applications in the ocean.
{"title":"Drowning Recognition for Ocean Surveillance using Computer Vision and Drone Control","authors":"M. Rakotondraibé, Tianyang Fang, J. Saniie","doi":"10.1109/eIT57321.2023.10187281","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187281","url":null,"abstract":"According to WHO's report from 2021, Drowning is the 3rd leading cause of unintentional death worldwide. The use of autonomous drones for drowning recognition can increase the survival rate and help lifeguards and rescuers with their life saving mission. This paper presents a real-time drowning recognition model and algorithm for ocean surveillance that can be implemented on a drone. The presented model has been trained using two different approaches and has 88% accuracy. Compared to the contemporary models of drowning recognition designed for swimming pools, the model presented is better suited for outdoor applications in the ocean.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130200867","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187374
T. T. Khoei, N. Kaabouch
Smart grid is an innovative technology that offers efficiency, low carbon emissions, and high energy storage. However, this promising technology has several shortcomings, including limited security. In this network, Intrusion Detection System (IDS) is one of the likely targeted systems that has limited security and is prone to several cyber vulnerabilities. To address a such challenge, several studies have been proposed to detect, classify, and mitigate these attacks using Artificial Intelligence (AI) techniques, although the proposed techniques in the literature suffer from high misdetection and false alarm rates. Additionally, limited data availability motivated the researchers to use another type of AI method, namely reinforcement learning to detect and classify attacks. In this paper, we propose a deep reinforcement learning-based technique, namely Q learning and capsule network as a deep learning model to detect attacks for IDS on smart grid networks. The benchmark of CICDDOs 2019 is selected to evaluate the model in terms of accuracy, detection, misdetection, false alarm rates, training time, and prediction time. We also investigate the performance of the proposed model based on discount values of 0.001 and 0.9. The experiments demonstrate that the proposed model has acceptable results, and the model with the lower discount values provides better results.
{"title":"ACapsule Q-Learning Based Reinforcement Model for Intrusion Detection System on Smart Grid","authors":"T. T. Khoei, N. Kaabouch","doi":"10.1109/eIT57321.2023.10187374","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187374","url":null,"abstract":"Smart grid is an innovative technology that offers efficiency, low carbon emissions, and high energy storage. However, this promising technology has several shortcomings, including limited security. In this network, Intrusion Detection System (IDS) is one of the likely targeted systems that has limited security and is prone to several cyber vulnerabilities. To address a such challenge, several studies have been proposed to detect, classify, and mitigate these attacks using Artificial Intelligence (AI) techniques, although the proposed techniques in the literature suffer from high misdetection and false alarm rates. Additionally, limited data availability motivated the researchers to use another type of AI method, namely reinforcement learning to detect and classify attacks. In this paper, we propose a deep reinforcement learning-based technique, namely Q learning and capsule network as a deep learning model to detect attacks for IDS on smart grid networks. The benchmark of CICDDOs 2019 is selected to evaluate the model in terms of accuracy, detection, misdetection, false alarm rates, training time, and prediction time. We also investigate the performance of the proposed model based on discount values of 0.001 and 0.9. The experiments demonstrate that the proposed model has acceptable results, and the model with the lower discount values provides better results.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130606181","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187309
Jack Li
Hands-on practice is an important fact to students' success, especially to the students who study in the field of Electrical Engineering and Electrical Engineering Technology (EET). Electronics systems have become so complex nowadays because of the high-density integrated circuits are widely used that it is hard for students to grasp the information about the systems in one course, especially microcontroller systems. In order to help students do more hands-on practice and understand a microprocessor system deeply, linking several courses together by using the same microcontroller was proposed in this paper. From the students' feedback, the setup really helps students do hands-on work on microprocesses with more confidence. The setup also helps the program reduce lab maintenance cost.
{"title":"Link Multiple Courses to Enhance Students' Hands-on Practice on Microprocessor Systems","authors":"Jack Li","doi":"10.1109/eIT57321.2023.10187309","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187309","url":null,"abstract":"Hands-on practice is an important fact to students' success, especially to the students who study in the field of Electrical Engineering and Electrical Engineering Technology (EET). Electronics systems have become so complex nowadays because of the high-density integrated circuits are widely used that it is hard for students to grasp the information about the systems in one course, especially microcontroller systems. In order to help students do more hands-on practice and understand a microprocessor system deeply, linking several courses together by using the same microcontroller was proposed in this paper. From the students' feedback, the setup really helps students do hands-on work on microprocesses with more confidence. The setup also helps the program reduce lab maintenance cost.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123973561","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187337
Ucchwas Talukder Utsha, B. Morshed
Cardiac disease, also known as cardiovascular disease, refers to a group of conditions that affect the heart and blood vessels. Diagnosis of cardiac disease typically involves a combination of medical history, physical examination, and various tests, such as electrocardiograms (ECG/EKG), echocardiograms, and stress tests. To address this concern, we introduce a mobile application called Smart-Health application, which can continuously monitor electrocardiogram signals and display Average Heart Rate (HR) along with the instantaneous HR. The aim of this project is to discover cardiac diseases so that doctors can monitor the accurate heart rate and take further actions based on the results. Smart-Health application typically works by collecting data from wrists or chest by electrodes. This data is then processed and analyzed to provide the user with insights into their health. We collected data from 10 participants and compared it with KardiaMobile (AliveCor®, Mountain View, CA, USA) commercial application. The error rate of the proposed algorithm depends on several factors, including the accuracy of the sensors used to capture the ECG signal, the algorithms used to process the signal, and the quality of the hardware and software components used to build the application. Experimental results show an accuracy of up to 95-99%. This Smart-Health application has the potential to improve health outcomes and reduce healthcare costs, making it a valuable tool for both individuals and healthcare providers.
心脏病，也被称为心血管疾病，是指一组影响心脏和血管的疾病。心脏病的诊断通常包括病史、体格检查和各种检查，如心电图(ECG/EKG)、超声心动图和压力测试。为了解决这一问题，我们推出了一款名为Smart-Health的移动应用程序，该应用程序可以连续监测心电图信号，并显示平均心率(HR)以及瞬时HR。这个项目的目的是发现心脏疾病，这样医生就可以监测准确的心率，并根据结果采取进一步的行动。智能健康应用通常通过电极从手腕或胸部收集数据。然后对这些数据进行处理和分析，为用户提供有关其健康状况的见解。我们收集了10名参与者的数据，并将其与KardiaMobile (AliveCor®，Mountain View, CA, USA)的商业应用程序进行了比较。该算法的错误率取决于几个因素，包括用于捕获心电信号的传感器的精度、用于处理信号的算法以及用于构建应用程序的硬件和软件组件的质量。实验结果表明，该方法的准确率可达95-99%。这种智能健康应用程序具有改善健康结果和降低医疗成本的潜力，使其成为个人和医疗保健提供者的宝贵工具。
{"title":"A Smartphone App for Real-time Heart Rate Computation from Streaming ECG/EKG data","authors":"Ucchwas Talukder Utsha, B. Morshed","doi":"10.1109/eIT57321.2023.10187337","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187337","url":null,"abstract":"Cardiac disease, also known as cardiovascular disease, refers to a group of conditions that affect the heart and blood vessels. Diagnosis of cardiac disease typically involves a combination of medical history, physical examination, and various tests, such as electrocardiograms (ECG/EKG), echocardiograms, and stress tests. To address this concern, we introduce a mobile application called Smart-Health application, which can continuously monitor electrocardiogram signals and display Average Heart Rate (HR) along with the instantaneous HR. The aim of this project is to discover cardiac diseases so that doctors can monitor the accurate heart rate and take further actions based on the results. Smart-Health application typically works by collecting data from wrists or chest by electrodes. This data is then processed and analyzed to provide the user with insights into their health. We collected data from 10 participants and compared it with KardiaMobile (AliveCor®, Mountain View, CA, USA) commercial application. The error rate of the proposed algorithm depends on several factors, including the accuracy of the sensors used to capture the ECG signal, the algorithms used to process the signal, and the quality of the hardware and software components used to build the application. Experimental results show an accuracy of up to 95-99%. This Smart-Health application has the potential to improve health outcomes and reduce healthcare costs, making it a valuable tool for both individuals and healthcare providers.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124778586","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187220
David Arnold, J. Saniie
Principal Component Analysis (PCA) is a versatile Unsupervised Learning (UL) technique for reducing the dimensionality of datasets. As a result, PCA is widely used in consumer and research applications as a preprocessing tool for identifying important features prior to further analysis. In instances where on-site personnel or developers do not have the expertise to apply UL techniques, third party processors are frequently retained. However, the release of client or proprietary data poses a substantial security risk. This risk increases the regulatory and contractual burden on analysts when interacting with sensitive or classified information. Homomorphic Encryption (HE) cryptosystems are a novel family of encryption algorithms that permit approximate addition and multiplication on encrypted data. When applied to UL models, such as PCA, experts may apply their expertise while maintaining data privacy. In order to evaluate the potential application of Homomorphic Encryption, we implemented Principal Component Analysis using the Microsoft SEAL HE libraries. The resulting implementation was applied to the MNIST Handwritten dataset for feature reduction and image reconstruction. Based on our results, HE considerably increased the time required to process the dataset. However, the HE algorithm is still viable for non-real-time applications as it had an average pixel error of near-zero for all image reconstructions.
主成分分析（PCA）是一种通用的无监督学习（UL）技术，可用于降低数据集的维度。因此，PCA 被广泛应用于消费和研究领域，作为一种预处理工具，用于在进一步分析前识别重要特征。在现场人员或开发人员不具备应用 UL 技术的专业知识的情况下，通常会使用第三方处理器。然而，泄露客户或专有数据会带来巨大的安全风险。这种风险增加了分析师在处理敏感或机密信息时的监管和合同负担。同态加密（HE）密码系统是一种新型加密算法，允许对加密数据进行近似加法和乘法运算。当应用于 UL 模型（如 PCA）时，专家们可以应用他们的专业知识，同时维护数据隐私。为了评估同态加密的潜在应用，我们使用微软 SEAL HE 库实施了主成分分析。由此产生的实现应用于 MNIST 手写数据集，用于特征还原和图像重建。根据我们的结果，HE 大大增加了处理数据集所需的时间。不过，HE 算法在非实时应用中仍然是可行的，因为它在所有图像重建中的平均像素误差几乎为零。
{"title":"Evaluation of Homomorphic Encryption for Privacy in Principal Component Analysis","authors":"David Arnold, J. Saniie","doi":"10.1109/eIT57321.2023.10187220","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187220","url":null,"abstract":"Principal Component Analysis (PCA) is a versatile Unsupervised Learning (UL) technique for reducing the dimensionality of datasets. As a result, PCA is widely used in consumer and research applications as a preprocessing tool for identifying important features prior to further analysis. In instances where on-site personnel or developers do not have the expertise to apply UL techniques, third party processors are frequently retained. However, the release of client or proprietary data poses a substantial security risk. This risk increases the regulatory and contractual burden on analysts when interacting with sensitive or classified information. Homomorphic Encryption (HE) cryptosystems are a novel family of encryption algorithms that permit approximate addition and multiplication on encrypted data. When applied to UL models, such as PCA, experts may apply their expertise while maintaining data privacy. In order to evaluate the potential application of Homomorphic Encryption, we implemented Principal Component Analysis using the Microsoft SEAL HE libraries. The resulting implementation was applied to the MNIST Handwritten dataset for feature reduction and image reconstruction. Based on our results, HE considerably increased the time required to process the dataset. However, the HE algorithm is still viable for non-real-time applications as it had an average pixel error of near-zero for all image reconstructions.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126349251","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187231
Zeeshan Abbas, K. Chong
Security has now become an essential part of communication on both sender and receiver's side. It is challenging to deliver comprehensive security against invaders since a lot of algorithms are expounded and can effortlessly get significant data by performing different hacking methods. High security-based algorithms like AES are nowadays used in various systems, as they present a high performance and is quite faster than most of stream-based encryption algorithms. Regardless of how reliable the technique is, the cipher-text always creates a doubt in brain when someone notices it, which makes the data prone to interception. Here arises another method of security to eliminate that suspicion, hence, we incorporate the confidential information into another format, such as an image, sound, video, or text and then transmit through the network. A novel security system based on three steps of hybrid architecture has been proposed in this paper by combining steganography and cryptography with codebooks. Two different keys are used to encrypt and then hide that highly secured encrypted message into the cover image. The message is encrypted first with AES algorithm and then placed at random positions in the cover image using codebook and KSA algorithm. AES encrypted message is mapped onto values of predefined codebooks then hide those encrypted message bits in LSBs of the cover image. The selected parameters are then passed on to the decryption side to recover the original message. Based on the achieved experimental results, it has outperformed the previous methodologies and without having the secret keys it is unfeasible to extract the message in a readable format.
{"title":"A Novel Approach Towards Fusion of Steganography and Cryptography for Enhanced Data Security using RGB Image","authors":"Zeeshan Abbas, K. Chong","doi":"10.1109/eIT57321.2023.10187231","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187231","url":null,"abstract":"Security has now become an essential part of communication on both sender and receiver's side. It is challenging to deliver comprehensive security against invaders since a lot of algorithms are expounded and can effortlessly get significant data by performing different hacking methods. High security-based algorithms like AES are nowadays used in various systems, as they present a high performance and is quite faster than most of stream-based encryption algorithms. Regardless of how reliable the technique is, the cipher-text always creates a doubt in brain when someone notices it, which makes the data prone to interception. Here arises another method of security to eliminate that suspicion, hence, we incorporate the confidential information into another format, such as an image, sound, video, or text and then transmit through the network. A novel security system based on three steps of hybrid architecture has been proposed in this paper by combining steganography and cryptography with codebooks. Two different keys are used to encrypt and then hide that highly secured encrypted message into the cover image. The message is encrypted first with AES algorithm and then placed at random positions in the cover image using codebook and KSA algorithm. AES encrypted message is mapped onto values of predefined codebooks then hide those encrypted message bits in LSBs of the cover image. The selected parameters are then passed on to the decryption side to recover the original message. Based on the achieved experimental results, it has outperformed the previous methodologies and without having the secret keys it is unfeasible to extract the message in a readable format.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132950872","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}
Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187222
Lila Areephanthu, B. Abegaz
This paper focuses on the verification of an object detection and avoidance method for autonomous vehicles to maneuver their way safely and efficiently. The model predictive control approach is explored and compared with other control approaches based on variables such as safe detection distance and safe operating time. The results indicate that the proposed approach could be promising for autonomous vehicles that often comprise various types of sensors and components and could otherwise be difficult to test and verify with traditional methods.
{"title":"Verification of a Predictive Method for Obstacle Detection and Safe Operation of Autonomous Vehicles","authors":"Lila Areephanthu, B. Abegaz","doi":"10.1109/eIT57321.2023.10187222","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187222","url":null,"abstract":"This paper focuses on the verification of an object detection and avoidance method for autonomous vehicles to maneuver their way safely and efficiently. The model predictive control approach is explored and compared with other control approaches based on variables such as safe detection distance and safe operating time. The results indicate that the proposed approach could be promising for autonomous vehicles that often comprise various types of sensors and components and could otherwise be difficult to test and verify with traditional methods.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134501586","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：