Pub Date : 2023-05-23DOI: 10.1109/sera57763.2023.10197804
{"title":"Message from Program Chairs","authors":"","doi":"10.1109/sera57763.2023.10197804","DOIUrl":"https://doi.org/10.1109/sera57763.2023.10197804","url":null,"abstract":"","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127085904","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197708
Deepak Panda, Piyush Basia, Kushal Nallavolu, Xin Zhong, Harvey P. Siy, Myoungkyu Song
A large corpus of software repositories enables an opportunity for using machine learning (ML) approaches to create new software engineering tools. In this paper, we propose a novel technique which leverages ML approaches for automating software engineering tasks and thus improves software quality. Our concrete goal is to (1) explore the abundance of predictable repetitive regularities of such a massive codebase, (2) develop an ML approach for training a statistical model to identify common patterns in software corpora, and then (3) use these patterns to statistically detect anomalous, likely buggy, program behavior that significantly deviates from these typical patterns. These internal regularities and repetitive properties of software can be captured as patterns to detect violations of these common patterns. Such violations have a critical impact on program behavior such as bugs, security vulnerabilities, or even program crashes. Our approach focuses on usage patterns of application programming interfaces (APIs). API usage patterns are commonly recurring, representative examples of how real-world applications use APIs in software corpora. These desirable patterns of API usage are learnable to validate or improve developers' implementations. This paper shows preliminary results that we use standard cross-entropy and perplexity to measure how surprising a test subject application is to a statistical model estimated from a software corpus. We continue to develop our approach and evaluate the effectiveness to focus on the following research questions. Are our ML models effectively trainable on large code corpora to learn desirable API usage patterns? How does the performance of our ML-based approach compare to state-of-the-art language models for software when learning API usage for detecting API misuse violations?
{"title":"A Statistical Method for API Usage Learning and API Misuse Violation Finding","authors":"Deepak Panda, Piyush Basia, Kushal Nallavolu, Xin Zhong, Harvey P. Siy, Myoungkyu Song","doi":"10.1109/SERA57763.2023.10197708","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197708","url":null,"abstract":"A large corpus of software repositories enables an opportunity for using machine learning (ML) approaches to create new software engineering tools. In this paper, we propose a novel technique which leverages ML approaches for automating software engineering tasks and thus improves software quality. Our concrete goal is to (1) explore the abundance of predictable repetitive regularities of such a massive codebase, (2) develop an ML approach for training a statistical model to identify common patterns in software corpora, and then (3) use these patterns to statistically detect anomalous, likely buggy, program behavior that significantly deviates from these typical patterns. These internal regularities and repetitive properties of software can be captured as patterns to detect violations of these common patterns. Such violations have a critical impact on program behavior such as bugs, security vulnerabilities, or even program crashes. Our approach focuses on usage patterns of application programming interfaces (APIs). API usage patterns are commonly recurring, representative examples of how real-world applications use APIs in software corpora. These desirable patterns of API usage are learnable to validate or improve developers' implementations. This paper shows preliminary results that we use standard cross-entropy and perplexity to measure how surprising a test subject application is to a statistical model estimated from a software corpus. We continue to develop our approach and evaluate the effectiveness to focus on the following research questions. Are our ML models effectively trainable on large code corpora to learn desirable API usage patterns? How does the performance of our ML-based approach compare to state-of-the-art language models for software when learning API usage for detecting API misuse violations?","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123532351","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197816
Zhang Xiao, T. Goto, Partha Ghosh, Tadaaki Kirishima, K. Tsuchida
Detection of novel game cheating tools is critical for ensuring fair online play. Such cheating tools are visual-based and effectively avoid detection because they do not change the data of game software. With the development and popularity of artificial intelligence technology, it has become easier for individuals to develop cheating tools, such as a new cheating tool for first-person shooter games that searches for characters on the game screen and automatically targets them. Therefore, in this study, a new cheat detection method is proposed using machine learning. The proposed method can be used to detect new cheating tools based on object detection.
{"title":"Detection of a Novel Object-Detection-Based Cheat Tool for First-Person Shooter Games Using Machine Learning","authors":"Zhang Xiao, T. Goto, Partha Ghosh, Tadaaki Kirishima, K. Tsuchida","doi":"10.1109/SERA57763.2023.10197816","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197816","url":null,"abstract":"Detection of novel game cheating tools is critical for ensuring fair online play. Such cheating tools are visual-based and effectively avoid detection because they do not change the data of game software. With the development and popularity of artificial intelligence technology, it has become easier for individuals to develop cheating tools, such as a new cheating tool for first-person shooter games that searches for characters on the game screen and automatically targets them. Therefore, in this study, a new cheat detection method is proposed using machine learning. The proposed method can be used to detect new cheating tools based on object detection.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125303034","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197780
Raad Haddad, D. E. D. I. Abou-Tair, Alá F. Khalifeh
Blockchain technology is widely used in many security-related Internet of Things (IoT) paradigms due to its dynamic and distributed architecture, which assures secure and private network access. Smart cities are one of these IoT applications in which security and privacy play a vital role. This paper proposes a blockchain-based verification process for smart nodes communication within the smart city, demonstrating the implementation details of the proposed security verification process and discussing potential security attacks.
{"title":"A Blockchain-Based Verification Process for Smart Cities","authors":"Raad Haddad, D. E. D. I. Abou-Tair, Alá F. Khalifeh","doi":"10.1109/SERA57763.2023.10197780","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197780","url":null,"abstract":"Blockchain technology is widely used in many security-related Internet of Things (IoT) paradigms due to its dynamic and distributed architecture, which assures secure and private network access. Smart cities are one of these IoT applications in which security and privacy play a vital role. This paper proposes a blockchain-based verification process for smart nodes communication within the smart city, demonstrating the implementation details of the proposed security verification process and discussing potential security attacks.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124703210","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197735
Ian Trawinski, H. Wimmer, Jongyeop Kim
Applying artificial intelligence and machine learning to analyzing network traffic has the potential to be transformative in protecting organizations from cyber threats. Intrusion detection systems (IDS) are historically rule-based; however, they could be improved. Applying machine learning in the form of Anomaly Detection could be the next step in preventing cyber threats from causing malicious activity on the network. Two algorithms that are implemented in anomaly detection through the use of Amazon SageMaker are Random Cut Forest (RCF) and XGBoost. The data for this project are the training and testing data set provided by the UNSW-15 data set. The models are created using the Jupiter Notebook on the Amazon SageMaker Studio Lab platform. The models were tested using the metrics of accuracy, precision, recall, and F1 score. The best-performing model was the XGBoost model, with an accuracy of 61.83%. The recall for this model was 96.49%, and the f1 score was 73.24%.
将人工智能和机器学习应用于网络流量分析，在保护组织免受网络威胁方面具有变革性的潜力。入侵检测系统(IDS)历来是基于规则的;然而，它们还可以改进。以异常检测的形式应用机器学习可能是防止网络威胁在网络上引起恶意活动的下一步。通过使用Amazon SageMaker实现异常检测的两种算法是Random Cut Forest (RCF)和XGBoost。本项目数据为UNSW-15数据集提供的训练和测试数据集。这些模型是使用Amazon SageMaker Studio Lab平台上的Jupiter Notebook创建的。使用准确性、精密度、召回率和F1分数对模型进行了测试。其中，XGBoost模型表现最好，准确率为61.83%。该模型的召回率为96.49%，f1得分为73.24%。
{"title":"Anomaly Detection in Intrusion Detection System using Amazon SageMaker","authors":"Ian Trawinski, H. Wimmer, Jongyeop Kim","doi":"10.1109/SERA57763.2023.10197735","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197735","url":null,"abstract":"Applying artificial intelligence and machine learning to analyzing network traffic has the potential to be transformative in protecting organizations from cyber threats. Intrusion detection systems (IDS) are historically rule-based; however, they could be improved. Applying machine learning in the form of Anomaly Detection could be the next step in preventing cyber threats from causing malicious activity on the network. Two algorithms that are implemented in anomaly detection through the use of Amazon SageMaker are Random Cut Forest (RCF) and XGBoost. The data for this project are the training and testing data set provided by the UNSW-15 data set. The models are created using the Jupiter Notebook on the Amazon SageMaker Studio Lab platform. The models were tested using the metrics of accuracy, precision, recall, and F1 score. The best-performing model was the XGBoost model, with an accuracy of 61.83%. The recall for this model was 96.49%, and the f1 score was 73.24%.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116450860","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197772
Jieun Kang, SuBi Kim, Yongik Yoon
The Advanced and radical development of IT technology and artificial intelligence technology have made it possible to develop advanced services Digital Twin, Metaverse, Metatwin-verse, etc using Artificial Intelligence(AI). The results induced from AI present the correct solution when AI performs accurate study and analysis. Specifically, real situations reflecting complex relationships between objects, results from real situations have to be adaptive to convergence situations and then it should be possible to draw conclusions and make decisions that are not limited to specific situations. So, it is essential to conduct AI based study and analysis by considering these real world characteristics to provide digital twin services based on metaverse. Recently, there are many studies on Graph Neural Network(GNN) and services applied to GNN for learning the relationship between objects detected in real situations. Accordingly, this paper proposes a metaverse-based Digital Twin Convergence Service(DTCS) including spatial elements strategy that is possible to draw accurate conclusions in a changing convergence situation. DTCS is able to conduct causal reasoning and association learning between objects considering directions and distances change characteristics between objects and this is possible to make correct solution and decision making in the process of simulation and analysis of digital twin. In that DTCS proceeds by considering distance and changing angle between objects, this overcomes the limitation of existing GNN which only considers the degree of association or assigns the same parameters to connected objects. DTCS would be possible to expand the advanced services of Metatwinverse in that it is possible to have robust learning based conclusions in real-time changing convergence situations.
{"title":"The Strategy of Digital Twin Convergence Service based on Metavers","authors":"Jieun Kang, SuBi Kim, Yongik Yoon","doi":"10.1109/SERA57763.2023.10197772","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197772","url":null,"abstract":"The Advanced and radical development of IT technology and artificial intelligence technology have made it possible to develop advanced services Digital Twin, Metaverse, Metatwin-verse, etc using Artificial Intelligence(AI). The results induced from AI present the correct solution when AI performs accurate study and analysis. Specifically, real situations reflecting complex relationships between objects, results from real situations have to be adaptive to convergence situations and then it should be possible to draw conclusions and make decisions that are not limited to specific situations. So, it is essential to conduct AI based study and analysis by considering these real world characteristics to provide digital twin services based on metaverse. Recently, there are many studies on Graph Neural Network(GNN) and services applied to GNN for learning the relationship between objects detected in real situations. Accordingly, this paper proposes a metaverse-based Digital Twin Convergence Service(DTCS) including spatial elements strategy that is possible to draw accurate conclusions in a changing convergence situation. DTCS is able to conduct causal reasoning and association learning between objects considering directions and distances change characteristics between objects and this is possible to make correct solution and decision making in the process of simulation and analysis of digital twin. In that DTCS proceeds by considering distance and changing angle between objects, this overcomes the limitation of existing GNN which only considers the degree of association or assigns the same parameters to connected objects. DTCS would be possible to expand the advanced services of Metatwinverse in that it is possible to have robust learning based conclusions in real-time changing convergence situations.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132578961","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197757
Prashanta Saha, C. Izurieta, Upulee Kanewala
Metamorphic testing is a technique that uses metamorphic relations (i.e., necessary properties of the software under test), to construct new test cases (i.e., follow-up test cases), from existing test cases (i.e., source test cases). Metamorphic testing allows for the verification of testing results without the need of test oracles (a mechanism to detect the correctness of the outcomes of a program), and it has been widely used in many application domains to detect real-world faults. Numerous investigations have been conducted to further improve the effectiveness of metamorphic testing. Recent studies have emerged suggesting a new research direction on the generation and selection of source test cases that are effective in fault detection. Herein, we present two important findings: i) a mutant reduction strategy that is applied to increase the testing efficiency of source test cases, and ii) a test suite minimization technique to help reduce the testing costs without trading off fault-finding effectiveness. To validate our results, an empirical study was conducted to demonstrate the increase in efficiency and fault-finding effectiveness of source test cases. The results from the experiment provide evidence to support our claims.
{"title":"A Test Suite Minimization Technique for Testing Numerical Programs","authors":"Prashanta Saha, C. Izurieta, Upulee Kanewala","doi":"10.1109/SERA57763.2023.10197757","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197757","url":null,"abstract":"Metamorphic testing is a technique that uses metamorphic relations (i.e., necessary properties of the software under test), to construct new test cases (i.e., follow-up test cases), from existing test cases (i.e., source test cases). Metamorphic testing allows for the verification of testing results without the need of test oracles (a mechanism to detect the correctness of the outcomes of a program), and it has been widely used in many application domains to detect real-world faults. Numerous investigations have been conducted to further improve the effectiveness of metamorphic testing. Recent studies have emerged suggesting a new research direction on the generation and selection of source test cases that are effective in fault detection. Herein, we present two important findings: i) a mutant reduction strategy that is applied to increase the testing efficiency of source test cases, and ii) a test suite minimization technique to help reduce the testing costs without trading off fault-finding effectiveness. To validate our results, an empirical study was conducted to demonstrate the increase in efficiency and fault-finding effectiveness of source test cases. The results from the experiment provide evidence to support our claims.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128553544","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197806
Adamu Hussaini, Cheng Qian, Y. Guo, Chao Lu, Wei Yu
The Internet of Things (IoT) paradigm is gradually becoming more prevalent through numerous devices and technologies, including sensors, actuators, microcontrollers, cloud-enabled services, and analytics. IoT objects gain intelligence by integrating with wireless sensor networks (WSNs), mobile computing and communication, and others. With sensors, smart things can be enabled by monitoring and identifying environmental changes related to motion, temperature, humidity, pressure, light, vibration, etc. To timely keep track of state changes, researchers are considering developing a cyber replicator, denoted as Digital Twin (DT), of real physical systems as a way to visualize, model, and work with complex cyber-physical systems (CPS). In this paper, we first refine the dataset to a format that can be easily used for deep learning (DL) experiments, IoT data pipeline development, data modeling and simulation, data aggregation, etc. We then demonstrate that DT data can be used to determine space occupancy based on the ambient light sensor, which tends to indicate occupancy in particular spaces because the building has smart lighting that will switch off when rooms are unoccupied after a certain time. Given the apparent developments in machine learning technology, it is clear that machine learning-based prediction has the ability to enhance resource utilization and further forecast future events. Particularly, we use a DT-based dataset and Long-Short-Term Memory (LSTM) neural network architecture to forecast the campus building’s internal temperature.
{"title":"Digital Twins of Smart Campus: Performance Evaluation Using Machine Learning Analysis","authors":"Adamu Hussaini, Cheng Qian, Y. Guo, Chao Lu, Wei Yu","doi":"10.1109/SERA57763.2023.10197806","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197806","url":null,"abstract":"The Internet of Things (IoT) paradigm is gradually becoming more prevalent through numerous devices and technologies, including sensors, actuators, microcontrollers, cloud-enabled services, and analytics. IoT objects gain intelligence by integrating with wireless sensor networks (WSNs), mobile computing and communication, and others. With sensors, smart things can be enabled by monitoring and identifying environmental changes related to motion, temperature, humidity, pressure, light, vibration, etc. To timely keep track of state changes, researchers are considering developing a cyber replicator, denoted as Digital Twin (DT), of real physical systems as a way to visualize, model, and work with complex cyber-physical systems (CPS). In this paper, we first refine the dataset to a format that can be easily used for deep learning (DL) experiments, IoT data pipeline development, data modeling and simulation, data aggregation, etc. We then demonstrate that DT data can be used to determine space occupancy based on the ambient light sensor, which tends to indicate occupancy in particular spaces because the building has smart lighting that will switch off when rooms are unoccupied after a certain time. Given the apparent developments in machine learning technology, it is clear that machine learning-based prediction has the ability to enhance resource utilization and further forecast future events. Particularly, we use a DT-based dataset and Long-Short-Term Memory (LSTM) neural network architecture to forecast the campus building’s internal temperature.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130081002","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197820
Sharad Sharma
There are a wide variety of mobile phone emergency response applications exist for both indoor and outdoor environments. However, outdoor applications mostly provide accident and navigation information to users, and indoor applications are limited to the unavailability of GPS positioning and WiFi access problems. This paper describes the proposed mobile augmented reality system (MARS) that allows both outdoor and indoor users to retrieve and manage information for emergency response and navigation that is spatially registered with the real world. The proposed MARS utilizes feature extraction for location sensing in indoor environments as during emergencies GPS and WiFi systems might not work. This paper describes the implementation of this MARS deployed on tablets and smartphones for building evacuation purposes. The MARS delivers critical evacuation information to smartphone users in the indoor environment and navigation information in the outdoor environments. A limited user study was conducted to test the effectiveness of the proposed MARS using the mobile phone usability questionnaire (MPUQ) framework. The results show that AR features were well integrated into the MARS and it will help identify the nearest exit in the building during the emergency evacuation.
{"title":"Mobile Augmented Reality System for Emergency Response","authors":"Sharad Sharma","doi":"10.1109/SERA57763.2023.10197820","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197820","url":null,"abstract":"There are a wide variety of mobile phone emergency response applications exist for both indoor and outdoor environments. However, outdoor applications mostly provide accident and navigation information to users, and indoor applications are limited to the unavailability of GPS positioning and WiFi access problems. This paper describes the proposed mobile augmented reality system (MARS) that allows both outdoor and indoor users to retrieve and manage information for emergency response and navigation that is spatially registered with the real world. The proposed MARS utilizes feature extraction for location sensing in indoor environments as during emergencies GPS and WiFi systems might not work. This paper describes the implementation of this MARS deployed on tablets and smartphones for building evacuation purposes. The MARS delivers critical evacuation information to smartphone users in the indoor environment and navigation information in the outdoor environments. A limited user study was conducted to test the effectiveness of the proposed MARS using the mobile phone usability questionnaire (MPUQ) framework. The results show that AR features were well integrated into the MARS and it will help identify the nearest exit in the building during the emergency evacuation.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127518144","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 : 2023-05-23DOI: 10.1109/SERA57763.2023.10197813
Jonathan Li, Steven Pugh, Honghe Zhou, Lin Deng, J. Dehlinger, Suranjan Chakraborty
Machine learning models are being increasingly relied on for many natural language processing tasks. However, these models are vulnerable to adversarial attacks, i.e., inputs designed to target models into making a wrong prediction. Among different methods of attacking a model, it is important to understand what attacks are effective, so that we can design countermeasures to protect the models. In this paper, we design and implement six adversarial attacks against natural language machine learning models. Then, we evaluate the effectiveness of these attacks using a fine-tuned distilled BERT model and 5,000 sample sentences from the SST-2 dataset. Our results indicate that the Word-replace attack affected the model the most, which reduces the F1-score of the model by 34%. The Word-delete attack is the least effective, but still reduces the model’s accuracy by 17%. Based on the experimental results, we discuss our insights and provide our recommendations for building robust natural language machine learning models.
{"title":"Experimental Evaluation of Adversarial Attacks Against Natural Language Machine Learning Models","authors":"Jonathan Li, Steven Pugh, Honghe Zhou, Lin Deng, J. Dehlinger, Suranjan Chakraborty","doi":"10.1109/SERA57763.2023.10197813","DOIUrl":"https://doi.org/10.1109/SERA57763.2023.10197813","url":null,"abstract":"Machine learning models are being increasingly relied on for many natural language processing tasks. However, these models are vulnerable to adversarial attacks, i.e., inputs designed to target models into making a wrong prediction. Among different methods of attacking a model, it is important to understand what attacks are effective, so that we can design countermeasures to protect the models. In this paper, we design and implement six adversarial attacks against natural language machine learning models. Then, we evaluate the effectiveness of these attacks using a fine-tuned distilled BERT model and 5,000 sample sentences from the SST-2 dataset. Our results indicate that the Word-replace attack affected the model the most, which reduces the F1-score of the model by 34%. The Word-delete attack is the least effective, but still reduces the model’s accuracy by 17%. Based on the experimental results, we discuss our insights and provide our recommendations for building robust natural language machine learning models.","PeriodicalId":211080,"journal":{"name":"2023 IEEE/ACIS 21st International Conference on Software Engineering Research, Management and Applications (SERA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130486190","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：