Pub Date : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00280
Mohamed Abdur Rahman, H. Shahriar, Victor A. Clincy, M. Hossain, M. Rahman
Machine learning has become widely accepted because of its diverse approaches to deal with a variety of cyber security issues. However, their capricious nature of security threats makes classical machine learning cyber systems vulnerable. Moreover, more samples in a big data dataset in classical machine learning approaches could produce the security defence systems weaken. It may create accurate outcomes by processing information which takes longer than expected, or observe poor accuracy because of inefficient training as well as other issues. However, quantum systems have the potential to produce atypical patterns which can not be possible to produce efficiently by classical systems, so we can postulate that quantum computers could use these advantages in that it could outperform the capabilities of classical computers on machine learning tasks. To be specific, an intrusion detection system can detect attack packets or sequence of attack packets at TCP/IP or other protocol level data based on certain patterns present or by profiling to detect anomalies. O(poly(n) gates are required to enable the use of potentially advantageous quantum algorithms with quantum states using he Quantum generative adversarial networks (qGAN) implemented by Qiskit which is a quantum computing tool of IBM.
{"title":"A Quantum Generative Adversarial Network-based Intrusion Detection System","authors":"Mohamed Abdur Rahman, H. Shahriar, Victor A. Clincy, M. Hossain, M. Rahman","doi":"10.1109/COMPSAC57700.2023.00280","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00280","url":null,"abstract":"Machine learning has become widely accepted because of its diverse approaches to deal with a variety of cyber security issues. However, their capricious nature of security threats makes classical machine learning cyber systems vulnerable. Moreover, more samples in a big data dataset in classical machine learning approaches could produce the security defence systems weaken. It may create accurate outcomes by processing information which takes longer than expected, or observe poor accuracy because of inefficient training as well as other issues. However, quantum systems have the potential to produce atypical patterns which can not be possible to produce efficiently by classical systems, so we can postulate that quantum computers could use these advantages in that it could outperform the capabilities of classical computers on machine learning tasks. To be specific, an intrusion detection system can detect attack packets or sequence of attack packets at TCP/IP or other protocol level data based on certain patterns present or by profiling to detect anomalies. O(poly(n) gates are required to enable the use of potentially advantageous quantum algorithms with quantum states using he Quantum generative adversarial networks (qGAN) implemented by Qiskit which is a quantum computing tool of IBM.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121722114","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}
Good code comments are of great value for program maintenance. However, during the development process, developers often neglect to update the corresponding comments when changing the code, which results in inconsistent comments and affects the maintainability of software. Studies have shown that even in widely used programs, there is a large number of outdated comments. Existing code comment update approaches use long short-term memory (LSTM) model based on encoder-decoder to capture the relationship between code changes and comment updates, to automatically update code comments. However, due to the complexity of code changes, the corresponding comments update results do not perform well. Thus, a Transformer-based automatic update approach for code comments called TBCUP is proposed in this paper. TBCUP uses the multi-head attention mechanism to learn the relationship between code change sequences and comment updates to update comments more accurately. In addition, TBCUP uses the Byte Pair Encoding (BPE) algorithm to build a unified vocabulary for code and corresponding comments to alleviate the problem of out–of-vocabulary (OOV) words while updating comments. With BPE, TBCUP can split or combine words to handle OOV words. The experimental results on the dataset containing 108k sets of code-comment co-evolution samples show that the accuracy of TBCUP is improved by 3.2% in comparison with CUP.
{"title":"TBCUP: A Transformer-based Code Comments Updating Approach","authors":"Shifan Liu, Zhanqi Cui, Xiang Chen, Junbiao Yang, Li Li, Liwei Zheng","doi":"10.1109/COMPSAC57700.2023.00119","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00119","url":null,"abstract":"Good code comments are of great value for program maintenance. However, during the development process, developers often neglect to update the corresponding comments when changing the code, which results in inconsistent comments and affects the maintainability of software. Studies have shown that even in widely used programs, there is a large number of outdated comments. Existing code comment update approaches use long short-term memory (LSTM) model based on encoder-decoder to capture the relationship between code changes and comment updates, to automatically update code comments. However, due to the complexity of code changes, the corresponding comments update results do not perform well. Thus, a Transformer-based automatic update approach for code comments called TBCUP is proposed in this paper. TBCUP uses the multi-head attention mechanism to learn the relationship between code change sequences and comment updates to update comments more accurately. In addition, TBCUP uses the Byte Pair Encoding (BPE) algorithm to build a unified vocabulary for code and corresponding comments to alleviate the problem of out–of-vocabulary (OOV) words while updating comments. With BPE, TBCUP can split or combine words to handle OOV words. The experimental results on the dataset containing 108k sets of code-comment co-evolution samples show that the accuracy of TBCUP is improved by 3.2% in comparison with CUP.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124943090","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00266
Federico D'Antoni, M. Bertazzoni, L. Vollero, M. Merone
Current management of Type 1 Diabetes mellitus (T1D) resorts to manual meal announcements from the patient to manage postprandial glycemia; nevertheless, suboptimal glycemic control is observed in real data, with the presence of many hypoglycemic and hyperglycemic events. The utilization of Continuous Glucose Monitoring (CGM) sensors and Artificial Intelligence (AI) is paving the way for improved and automated glycemic control. A step in this direction is represented by the automation of meal detection, which would not require patients to perform tasks such as carbohydrate estimation and meal announcement that are error-prone, especially for children and elderly patients.In this work, we investigate several AI models for meal detection from in silico data of 10 adults, 10 adolescents, and 10 children with T1D using only CGM data, and compare them to the standard detection method based on the glycemic threshold. We generate 30 days of data per patient that include 5 meals per day and introduce human error on carbohydrate estimation to make data more similar to the real ones. The AI models can detect more than 81% of meals from any cohort of patients while producing a relatively small amount of false positives. The feedforward neural network, the support vector machine, and the threshold method are the most promising meal detection strategies for adult, adolescent, and child populations, respectively, and may improve patients’ health and disease management.
{"title":"Identification of the Optimal Meal Detection Strategy for Adults, Adolescents, and Children with Type 1 Diabetes: an in Silico Validation","authors":"Federico D'Antoni, M. Bertazzoni, L. Vollero, M. Merone","doi":"10.1109/COMPSAC57700.2023.00266","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00266","url":null,"abstract":"Current management of Type 1 Diabetes mellitus (T1D) resorts to manual meal announcements from the patient to manage postprandial glycemia; nevertheless, suboptimal glycemic control is observed in real data, with the presence of many hypoglycemic and hyperglycemic events. The utilization of Continuous Glucose Monitoring (CGM) sensors and Artificial Intelligence (AI) is paving the way for improved and automated glycemic control. A step in this direction is represented by the automation of meal detection, which would not require patients to perform tasks such as carbohydrate estimation and meal announcement that are error-prone, especially for children and elderly patients.In this work, we investigate several AI models for meal detection from in silico data of 10 adults, 10 adolescents, and 10 children with T1D using only CGM data, and compare them to the standard detection method based on the glycemic threshold. We generate 30 days of data per patient that include 5 meals per day and introduce human error on carbohydrate estimation to make data more similar to the real ones. The AI models can detect more than 81% of meals from any cohort of patients while producing a relatively small amount of false positives. The feedforward neural network, the support vector machine, and the threshold method are the most promising meal detection strategies for adult, adolescent, and child populations, respectively, and may improve patients’ health and disease management.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125002837","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00108
David Faragó, Michael Färber, Christian Petrov
Commit messages (CMs) are an essential part of version control. By providing important context in regard to what has changed and why, they strongly support software maintenance and evolution. But writing good CMs is difficult and often neglected by developers. So far, there is no tool suitable for practice that automatically assesses how well a CM is written, including its meaning and context. Since this task is challenging, we ask the research question: how well can the CM quality, including semantics and context, be measured with machine learning methods? By considering all rules from the most popular CM quality guideline, creating datasets for those rules, and training and evaluating state-of-the-art machine learning models to check those rules, we can answer the research question with: sufficiently well for practice, with the lowest F1 score of 82.9%, for the most challenging task. We develop a full-fledged open-source framework that checks all these CM quality rules. It is useful for research, e.g., automatic CM generation, but most importantly for software practitioners to raise the quality of CMs and thus the maintainability and evolution speed of their software.
{"title":"A Full-fledged Commit Message Quality Checker Based on Machine Learning","authors":"David Faragó, Michael Färber, Christian Petrov","doi":"10.1109/COMPSAC57700.2023.00108","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00108","url":null,"abstract":"Commit messages (CMs) are an essential part of version control. By providing important context in regard to what has changed and why, they strongly support software maintenance and evolution. But writing good CMs is difficult and often neglected by developers. So far, there is no tool suitable for practice that automatically assesses how well a CM is written, including its meaning and context. Since this task is challenging, we ask the research question: how well can the CM quality, including semantics and context, be measured with machine learning methods? By considering all rules from the most popular CM quality guideline, creating datasets for those rules, and training and evaluating state-of-the-art machine learning models to check those rules, we can answer the research question with: sufficiently well for practice, with the lowest F1 score of 82.9%, for the most challenging task. We develop a full-fledged open-source framework that checks all these CM quality rules. It is useful for research, e.g., automatic CM generation, but most importantly for software practitioners to raise the quality of CMs and thus the maintainability and evolution speed of their software.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122393108","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00129
Jacob McCalip, Mandil Pradhan, Kecheng Yang
Developing autonomous driving models through reinforcement learning is gaining widespread prominence. However, a pervasive problem is developing obstacle avoidance systems. Specifically, optimizing path completion times while avoiding objects is an underdeveloped area of research. AWS DeepRacer’s platform provides a powerful architecture for engineering and analyzing autonomous models. Using AWS DeepRacer, we integrate two pathfinding algorithms, A* and Line-of-Sight (LoS), into this paradigm of autonomous driving. LoS is a novel algorithm that incrementally updates the model’s heading angles to amply reach its destination. We trained three types of models: Centerline, A*, and LoS. The Centerline model utilizes logic from AWS and is practically the only model used by the AWS DeepRacer community that avoids objects. We developed models from A* and LoS that outperformed the default models in time per lap while maintaining commensurate stability.
{"title":"Reinforcement Learning Approaches for Racing and Object Avoidance on AWS DeepRacer","authors":"Jacob McCalip, Mandil Pradhan, Kecheng Yang","doi":"10.1109/COMPSAC57700.2023.00129","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00129","url":null,"abstract":"Developing autonomous driving models through reinforcement learning is gaining widespread prominence. However, a pervasive problem is developing obstacle avoidance systems. Specifically, optimizing path completion times while avoiding objects is an underdeveloped area of research. AWS DeepRacer’s platform provides a powerful architecture for engineering and analyzing autonomous models. Using AWS DeepRacer, we integrate two pathfinding algorithms, A* and Line-of-Sight (LoS), into this paradigm of autonomous driving. LoS is a novel algorithm that incrementally updates the model’s heading angles to amply reach its destination. We trained three types of models: Centerline, A*, and LoS. The Centerline model utilizes logic from AWS and is practically the only model used by the AWS DeepRacer community that avoids objects. We developed models from A* and LoS that outperformed the default models in time per lap while maintaining commensurate stability.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131169224","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00224
Martin Molan, Junaid Ahmed Khan, Andrea Bartolini, R. Turra, G. Pedrazzi, Michael Cochez, A. Iosup, D. Roman, Jože M. Rožanec, A. Varbanescu, R.-C. Prodan
Modeling and understanding an expensive next-generation data center operating at a sustainable exascale performance remains a challenge yet to solve. The paper presents the approach taken by the Graph-Massivizer project, funded by the European Union, towards a sustainable data center, targeting a massive graph representation and analysis of its digital twin. We introduce five interoperable open-source tools that support this undertaking, creating an automated, sustainable loop of graph creation, analytics, optimization, sustainable resource management, and operation, emphasizing state-of-the-art progress. We plan to employ the tools for designing a massive data center graph, representing a digital twin describing spatial, semantic, and temporal relationships between the monitoring metrics, hardware nodes, cooling equipment, and jobs. The project aims to strengthen Bologna Technopole as a leading European supercomputing and big data hub offering sustainable green computing for improved societally relevant science throughput.
{"title":"The Graph-Massivizer Approach Toward a European Sustainable Data Center Digital Twin","authors":"Martin Molan, Junaid Ahmed Khan, Andrea Bartolini, R. Turra, G. Pedrazzi, Michael Cochez, A. Iosup, D. Roman, Jože M. Rožanec, A. Varbanescu, R.-C. Prodan","doi":"10.1109/COMPSAC57700.2023.00224","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00224","url":null,"abstract":"Modeling and understanding an expensive next-generation data center operating at a sustainable exascale performance remains a challenge yet to solve. The paper presents the approach taken by the Graph-Massivizer project, funded by the European Union, towards a sustainable data center, targeting a massive graph representation and analysis of its digital twin. We introduce five interoperable open-source tools that support this undertaking, creating an automated, sustainable loop of graph creation, analytics, optimization, sustainable resource management, and operation, emphasizing state-of-the-art progress. We plan to employ the tools for designing a massive data center graph, representing a digital twin describing spatial, semantic, and temporal relationships between the monitoring metrics, hardware nodes, cooling equipment, and jobs. The project aims to strengthen Bologna Technopole as a leading European supercomputing and big data hub offering sustainable green computing for improved societally relevant science throughput.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121636707","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00153
Zhaoran Wang, Xiangyu Bai, Yufeng Han
Power infrastructure and its connectivity are central to building a smart grid. The infrastructure regional subsidence caused by environmental factors or geological hazards may devastate grid systems. Therefore, it is critical to forecasting the infrastructure regional subsidence in smart grids. In this study, we used an InSAR time series subsidence dataset based on satellite remote sensing images to train, test and compare four deep learning-based Transformer series prediction models using transfer learning to achieve subsidence crisis monitoring and prediction in smart grid infrastructure areas, considering the influence of environmental factors on infrastructure regional subsidence. Meanwhile, an GIS for subsidence crisis prediction in smart grid infrastructure areas was developed based on the Autoformer model. It helps the power industry maintain the smart grid more efficiently and accurately while also saving a lot of money and labor.
{"title":"Deep Learning for Regional Subsidence Crisis Prediction in Smart Grid Infrastructure","authors":"Zhaoran Wang, Xiangyu Bai, Yufeng Han","doi":"10.1109/COMPSAC57700.2023.00153","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00153","url":null,"abstract":"Power infrastructure and its connectivity are central to building a smart grid. The infrastructure regional subsidence caused by environmental factors or geological hazards may devastate grid systems. Therefore, it is critical to forecasting the infrastructure regional subsidence in smart grids. In this study, we used an InSAR time series subsidence dataset based on satellite remote sensing images to train, test and compare four deep learning-based Transformer series prediction models using transfer learning to achieve subsidence crisis monitoring and prediction in smart grid infrastructure areas, considering the influence of environmental factors on infrastructure regional subsidence. Meanwhile, an GIS for subsidence crisis prediction in smart grid infrastructure areas was developed based on the Autoformer model. It helps the power industry maintain the smart grid more efficiently and accurately while also saving a lot of money and labor.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132717498","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00086
Junhao Li, Yujian Zhang
Hybrid fuzzing combines fuzzing and concolic execution which leverages the high-throughput feature of fuzzing to explore easy-to-reach code, and the powerful constraint solving capability of concolic execution to explore code wrapped in complex constraints. Based on our observations, existing hybrid fuzzers are still not efficient for the following two reasons. First, fuzzing often gets stuck in deep paths leading to the delayed discovery of vulnerabilities. Second, coarse-grained interaction strategies cannot effectively launch concolic execution. To solve the above problems, we propose a constraint-guided hybrid fuzzing approach (CGHF) that leverages the constraints’ static analysis information and dynamic execution information. CGHF contains two main techniques: an evolutionary algorithm based on path exploration difficulty and an interaction strategy guided by the execution state of constraints. Specifically, in the fuzzing phase, we evaluate the path exploration difficulty and guide the fuzzer to explore in the order of difficulty from low to high. In addition, we design a coordinator to monitor the constraints’ dynamic execution information and select the most deserving constraints to be solved for the concolic execution. We implement a prototype called SILK and compare its effectiveness on eight open source programs with other state-of-the-art fuzzers. The results show that SILK improved path coverage by 10%-45% and branch coverage by 5%-10% compared with other fuzzers.
{"title":"SILK: Constraint-guided Hybrid Fuzzing","authors":"Junhao Li, Yujian Zhang","doi":"10.1109/COMPSAC57700.2023.00086","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00086","url":null,"abstract":"Hybrid fuzzing combines fuzzing and concolic execution which leverages the high-throughput feature of fuzzing to explore easy-to-reach code, and the powerful constraint solving capability of concolic execution to explore code wrapped in complex constraints. Based on our observations, existing hybrid fuzzers are still not efficient for the following two reasons. First, fuzzing often gets stuck in deep paths leading to the delayed discovery of vulnerabilities. Second, coarse-grained interaction strategies cannot effectively launch concolic execution. To solve the above problems, we propose a constraint-guided hybrid fuzzing approach (CGHF) that leverages the constraints’ static analysis information and dynamic execution information. CGHF contains two main techniques: an evolutionary algorithm based on path exploration difficulty and an interaction strategy guided by the execution state of constraints. Specifically, in the fuzzing phase, we evaluate the path exploration difficulty and guide the fuzzer to explore in the order of difficulty from low to high. In addition, we design a coordinator to monitor the constraints’ dynamic execution information and select the most deserving constraints to be solved for the concolic execution. We implement a prototype called SILK and compare its effectiveness on eight open source programs with other state-of-the-art fuzzers. The results show that SILK improved path coverage by 10%-45% and branch coverage by 5%-10% compared with other fuzzers.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133423909","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00039
Jinyi Wang, Tong Li, Hongyu Gao
Faced with so many mobile applications in the app store, users have difficulties finding their preferred mobile applications. Existing studies do not comprehensively consider implicit feedback in mobile applications and thus do not combine behavioral information and published information together to make recommendations. This paper proposes a novel method to recommend mobile applications based on metagraph embedding using the combination of behavioral information and published information. Specifically, this paper constructed a conceptual model using the combinations of behavioral information and published information that could well portray users and mobile applications. Based on this conceptual model, six metagraphs are designed to interpret the multidimensional relationships between users and mobile applications in the model. By random walking guided by each metagraph, a series of node sequences that could express node neighborhood are obtained. Finally, the similarity between users and apps is calculated using the embedded vector of each node, and the recommendations are given to the user. Based on a real-world dataset, we evaluate the performance of our method. The experimental result shows that our method outperforms existing models and methods in all metrics, in which the average F1-measure increases by 19.21%, and the average NDCG increases by 4.99%.
{"title":"Application Recommendation based on Metagraphs: Combining Behavioral and Published Information","authors":"Jinyi Wang, Tong Li, Hongyu Gao","doi":"10.1109/COMPSAC57700.2023.00039","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00039","url":null,"abstract":"Faced with so many mobile applications in the app store, users have difficulties finding their preferred mobile applications. Existing studies do not comprehensively consider implicit feedback in mobile applications and thus do not combine behavioral information and published information together to make recommendations. This paper proposes a novel method to recommend mobile applications based on metagraph embedding using the combination of behavioral information and published information. Specifically, this paper constructed a conceptual model using the combinations of behavioral information and published information that could well portray users and mobile applications. Based on this conceptual model, six metagraphs are designed to interpret the multidimensional relationships between users and mobile applications in the model. By random walking guided by each metagraph, a series of node sequences that could express node neighborhood are obtained. Finally, the similarity between users and apps is calculated using the embedded vector of each node, and the recommendations are given to the user. Based on a real-world dataset, we evaluate the performance of our method. The experimental result shows that our method outperforms existing models and methods in all metrics, in which the average F1-measure increases by 19.21%, and the average NDCG increases by 4.99%.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131988555","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 : 2023-06-01DOI: 10.1109/COMPSAC57700.2023.00276
I. Cho, D. Towey, Pushpendu Kar
Android compilers play a crucial role in Android app development. The correctness of the apps relies on the compilers because the source code of the app is translated into the target language by the compilers. The use of obfuscators is becoming the standard in app development to prevent reverse engineering or code tampering. Despite their importance, both compilers and obfuscators lack an oracle, which is the mechanism to determine the correctness of the execution, and hence they can be called untestable software. Metamorphic Testing (MT) is a state-of-the-art testing method that can test untestable software. MT tests software based on Metamorphic Relations (MRs). Recent studies have shown that program transformation, an MT-based compiler-testing strategy, is highly effective in revealing bugs in compilers. However, this strategy requires sophisticated tools that could take significant time to develop. Therefore, program transformation using obfuscators is proposed. Based on research into testing obfuscators using MT, it is suggested that an MT-based compiler-testing strategy could be achieved by using obfuscators. In addition, this method has the potential to detect bugs in both compilers and obfuscators. This paper reports on our experience using MT techniques to test compilers and obfuscators. We present three related MRs, two of which uncover evidence of faults.
{"title":"Using Obfuscators to Test Compilers: A Metamorphic Experience","authors":"I. Cho, D. Towey, Pushpendu Kar","doi":"10.1109/COMPSAC57700.2023.00276","DOIUrl":"https://doi.org/10.1109/COMPSAC57700.2023.00276","url":null,"abstract":"Android compilers play a crucial role in Android app development. The correctness of the apps relies on the compilers because the source code of the app is translated into the target language by the compilers. The use of obfuscators is becoming the standard in app development to prevent reverse engineering or code tampering. Despite their importance, both compilers and obfuscators lack an oracle, which is the mechanism to determine the correctness of the execution, and hence they can be called untestable software. Metamorphic Testing (MT) is a state-of-the-art testing method that can test untestable software. MT tests software based on Metamorphic Relations (MRs). Recent studies have shown that program transformation, an MT-based compiler-testing strategy, is highly effective in revealing bugs in compilers. However, this strategy requires sophisticated tools that could take significant time to develop. Therefore, program transformation using obfuscators is proposed. Based on research into testing obfuscators using MT, it is suggested that an MT-based compiler-testing strategy could be achieved by using obfuscators. In addition, this method has the potential to detect bugs in both compilers and obfuscators. This paper reports on our experience using MT techniques to test compilers and obfuscators. We present three related MRs, two of which uncover evidence of faults.","PeriodicalId":296288,"journal":{"name":"2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132218891","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：