{"title":"A cybersecurity risk assessment of electric vehicle mobile applications: findings and recommendations","authors":"Zia-Ullah Muhammad, Zahid Anwar, B. Saleem","doi":"10.1109/ICAI58407.2023.10136682","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136682","url":null,"abstract":"Electric vehicles (EVs) are becoming increasingly prevalent, with many manufacturers and third-party developers creating mobile applications to manage and monitor their use. The security of these applications is critical, as they handle sensitive information such as vehicle location, statistics, and personally identifiable information (PII) stored in the mobile device. This research conducts a cybersecurity risk assessment of several popular applications developed by (1) EV manufacturers including Tesla, Mercedes, BMW, Nissan, and Volkswagen and (2) third-party developers such as EVConnect, EVgo, Plugshare, ChargeHub, and EV-Energy. Our findings reveal a range of security vulnerabilities, including insecure communication, lack of encryption for data transmission, and insecure data storage. The list of mobile permissions acquired by these applications and the potential consequences of a security breach are also discussed. Moreover, the article highlights additional features provided by third parties that are not available in applications developed by EV manufacturers and attract users into installing the same. Finally, safeguards and defensive controls are proposed for hardening these applications to prevent security incidents.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129138276","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}
{"title":"Intelligent Predictive Model for Hepatitis C","authors":"Mehreen Shahzadi, Faisal Bukhari, Numan Shafi","doi":"10.1109/ICAI58407.2023.10136685","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136685","url":null,"abstract":"Hepatitis C is the liver's festering that can lead to severe liver damage, usually caused by the hepatitis C virus. Hepatitis C has different stages. It is tough to cure in it's last stages; at the same time, it is expensive and painful process. The current research, however, is an alternative precaution to this issue. Hepatitis C can be predicted early by using multiple factors. The dataset related to hepatitis C was not publicly available. To overcome this challenge, the healthy and HCV effected samples were collected from different hospitals in Punjab. A questionnaire based survey was taken including different HCV related factor i.e. gender, weight loss, hives/ rashes, swelling, jaundice, drug addiction history, hepatic encephalopa-thy (drowsiness, slurred speech), Ascites (fluid buildup in belly/ abdomen), spider angiomas (Spiderlike blood vessels), shared syringe usage, medical history, and severeness. Different cleaning, scaling, and feature selection techniques were applied to collect the best feature data. After selection, various machine learning algorithms were applied. Random forest, KNN, Decision Tree, SVC, and MLP were used, but MLP yielded optimal results in all classification algorithms. We have gained 95.9 % accuracy when tested on unknown data based on the MLP model. As the predictions' results were satisfactory, it would be helpful for the people and act as a critical awareness.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130358525","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}
{"title":"Deep Learning-based Analysis and Classification of COVID Patients Through CT Images","authors":"Maria Alam, M. Akram, Wajeha Fareed","doi":"10.1109/ICAI58407.2023.10136653","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136653","url":null,"abstract":"COVID 19 disease also known as SARS-CoV-2 has spread rapidly all over the world, crippling industries all around the world, caused many death and affected life in all aspects. SARS-CoV-2 has become a global pandemic within three months. Even though some test facilities has been available, but they are not useful because of varying symptoms. In severe cases most patients have been diagnosed by lung infection, most of the patients with lungs infection go unnoticed or have been confused with pneumonia which caused the rise in mortality rate. Modern facilities, such as artificial intelligence and machine learning, and neural network-based technologies can be used to resolve these issues. In this research, we present a technique for lung CT-scan images analysis to classify the infected patients, for this we have used the lightweight neural network-based EfficientNet using a publicly available dataset and achieved an accuracy of 98.00 %. Other datasets have also been tested on trained weights of EfficientNet classification architecture and accuracy of 86.62 % and 88.98% is achieved. We also used specialized pre-processing techniques on the dataset, which gives the accuracy of 99.90%, and fine-tuned the trained weights on two other datasets and achieved an accuracy of 99.89% and 99.18% respectively. Also, it has been proved that training weights of the neural network on one dataset, could detect infected patients and give good accuracy on any other CT scan datasets.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"423 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133836785","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}
Sobia Arshad, Rida Zanib, Adeel Akram, Ali Haider, Talha Saeed, Muhammad Shaheem Raza
{"title":"ML-IBotD: Machine Learning based Intelligent Botnet Detection","authors":"Sobia Arshad, Rida Zanib, Adeel Akram, Ali Haider, Talha Saeed, Muhammad Shaheem Raza","doi":"10.1109/ICAI58407.2023.10136647","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136647","url":null,"abstract":"With the advancements in communication technologies, an abundance of smart devices and internet-based applications in every walk of human life has resulted in the production of a huge number of data transmissions over the internet. In line with this emergence, the number of cybersecurity attacks is also rising. Among notable network attacks like mal ware, phishing, etc., we focused on botnet attacks which can cause huge damage on a large scale because botnet works in network form which appears as an adverse risk for the internet. In the botnet, there are many compromised systems known as bots controlled by the botmaster. On the other hand, Machine Learning (ML) is playing an important role in the detection of such network attacks with notable accuracy. In this paper, we select a dataset of CIC-IDS2017 due to its real interpretation of botnets. Then flows are extracted and then relevant four features are selected from the flows. In this paper, we apply four classifiers of SVM, KNN, DT, and Ensemble classifier on a real dataset of CIC-IDS2017. The highest achieved testing accuracy is 99.56% with the Ensemble classifier.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115844524","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}
Iqra Siddiqui, Fizza Rubab, Haania Siddiqui, Abdul Samad
{"title":"Poet Attribution of Urdu Ghazals using Deep Learning","authors":"Iqra Siddiqui, Fizza Rubab, Haania Siddiqui, Abdul Samad","doi":"10.1109/ICAI58407.2023.10136675","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136675","url":null,"abstract":"Poet attribution focuses on determining ownership of a piece of poetry by insights obtained from analyzing his existing poetry. Its significance is immense including in detection of plagiarism and characterization of poetry of a poet. Urdu, Pakistan's lingua franca with the richest poetic tradition, has been a subject of misinformation and misattribution. This paper presents a novel approach to poet attribution in Urdu Ghazals through the application of machine and deep learning models. Our aim is to establish an accurate and comprehensive characterization of ghazals that captures the unique writing style of each poet. To achieve this, we trained and tested a range of machine learning, deep learning, and transformer-based classification models on a dataset containing 17,609 couplets of 15 notable ghazal poets. We used classifiers such as SVM and logistic regression to obtain preliminary results, achieving an accuracy of 64% with SVM. However, to achieve even better results, we employed deep learning models such as MLP, CNNs, and GRUs, with LSTMs resulting in the highest accuracy of 59.96%. We then used transformer-based models, including roBERTa and BERT, which achieved an outstanding accuracy of approximately 80% in classifying 15 poets. This work represents a significant contribution to the field of computational poetry analysis, as it is the first to explore poet attribution in Urdu Ghazals using deep learning and transformer-based models. Our analytical approach enables us to examine and analyze each model's capabilities in capturing the writing style of Urdu Ghazal poets, leading to a more comprehensive and accurate characterization of these works.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125913575","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}
{"title":"Imitation Learning for Autonomous Driving Cars","authors":"Omer Qureshi, Muhammad Nouman Durrani, S. Raza","doi":"10.1109/ICAI58407.2023.10136686","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136686","url":null,"abstract":"The world is the middle of another industrial revolution. But this time, instead of the steam engines, the real revolution will be led by computer scientists across the globe who will forever change the way we interact with our environment. A small subset of groundbreaking research has been going on in the field of autonomous driving to ensure the safety of passengers and human comfort. Autonomous driving, which primarily relies on the subset of machine learning i.e., imitation learning has been a subject of research for several decades now. The critical problem in autonomous driving is predicting the steering angles of the vehicle. Behavior cloning is a form of imitation learning and it learns from the actions of human experts. However, imitation learning has its own set of challenges and performs poorly in certain conditions. In this research a new algorithm is proposed, CNNO, to predict the steering angles of the vehicle. It has five convolution layers, two max pool layers, four fully connected layers, flatten layer, and a drop-out layer. It is subsequently compared against CNN-Neural Circuit Policy, CNN, ResNet50, VGG16, and VGG19 architectures. The proposed algorithm has shown to give the best evaluation error results from epochs 10, 30 & 50 and the best training error in epoch 70.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132580714","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}
{"title":"Machine Learning Based Classification of crystal system using rendered images from X-ray diffraction (XRD) dataset","authors":"A. Hamza, Umar Hayat, Wahid Hussain, Anam Mumtaz","doi":"10.1109/ICAI58407.2023.10136622","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136622","url":null,"abstract":"X-ray diffraction(XRD) is an essential characterization technique to study the properties of the materials. Finding a material's crystal system is an important step in its analysis. So, the process should be fast as well as accurate. In total there are seven crystal systems: triclinic, monoclinic, orthorhombic, tetragonal, trigonal, hexagonal, and cubic. Previous studies have worked on finding the material crystal structure by introducing machine learning approaches. In, recent studies the X-ray diffraction(XRD) dataset in the tabular form was used to train a machine learning model to classify the material's crystal system. The machine learning models trained on the tabular X-ray diffraction(XRD) dataset didn't maximize their performance. In the scope of this study rendered X-ray diffraction(XRD) images had been used to maximize the performance of the machine learning models. By using the rendered images as input from the X-ray diffraction(XRD) tabular dataset the machine learning model was able to achieve an accuracy of 98%-99%. The final findings had shown that rendered images datasets had improved the machine learning model's ability to correctly classify the crystal systems of materials.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133379361","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}
{"title":"3rd International Conference on Artificial Intelligence (ICAI) 2023","authors":"","doi":"10.1109/icai58407.2023.10136673","DOIUrl":"https://doi.org/10.1109/icai58407.2023.10136673","url":null,"abstract":"","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115440473","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}
Leethar Yao, Bo-Yu Lin, Qazi Mazhar ul Haq, Ihtesham Ul Islam
{"title":"Unsupervised Cross-Domain Adaptation through Mutual Mean Learning and GANs for Person Re-identification","authors":"Leethar Yao, Bo-Yu Lin, Qazi Mazhar ul Haq, Ihtesham Ul Islam","doi":"10.1109/ICAI58407.2023.10136664","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136664","url":null,"abstract":"Unsupervised cross-domain adaptation is a challenging task for person re-identification due to the unavailability of target domain labels. Among existing methods, pseudo-Iabels-based methods have considerable performance but most of them use target domain data without labels which are challenging difficult for the target model to learn enough features. In this paper, we use generative based models that generate more target data. In cooperation with the generative model, a mutual learning model is used to transfer knowledge of one model to another model that ultimately improves overall model performance. Ex-tensive experiments are performed on Duke and Market datasets that significantly achieve improved performance in comparison to state-of-the-art methods.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122161559","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}
Haris Ijaz, Hajrah Sultan, Mishal Altaf, Asim Waris
{"title":"Embedded Skin Lesion Segmentation using Lightweight Encoder-Decoder Architectures","authors":"Haris Ijaz, Hajrah Sultan, Mishal Altaf, Asim Waris","doi":"10.1109/ICAI58407.2023.10136688","DOIUrl":"https://doi.org/10.1109/ICAI58407.2023.10136688","url":null,"abstract":"Skin cancer is a global health concern that might be alleviated by embedded device-assisted diagnosis due to the limited number of dermatologists in many regions. An embedded device integrated with a camera for skin cancer diagnosis is of great interest worldwide, potentially enhancing mobile dermo-scopic diagnosis for the most malignant skin cancer, melanoma. The automatic segmentation of skin lesions from images is a crucial step towards reaching this objective. Deep learning-based models provide state-of-the-art accuracy in dermoscopic image analysis and diagnosis. Deep learning, on the other hand, has high computation costs, making it difficult to integrate such models on an embedded platform with limited resources. For this purpose, we proposed lightweight encoder-decoder deep learning architectures, referred to as MobileUNet and EfficientUNet, with the encoder based on the MobileNetV2 bottleneck block and the EfficientNetB0 MBConv block, respectively, and the decoder being identical to the baseline UNet model. The proposed architectures are evaluated on two publicly available datasets, ISIC 2017 and ISIC 2018. Models run efficiently on embedded platforms, achieving up to 12 percent higher performance compared to the baseline model with minimal power and memory requirements without compromising accuracy or the Jaccard index compared to the baseline model.","PeriodicalId":161809,"journal":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126808698","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}