Skip to main content

Research Repository

Advanced Search

All Outputs (10)

State of Practice: LLMs in Software Engineering and Software Architecture (2024)
Presentation / Conference Contribution
Jahic, J., & Sami, A. (2024, June). State of Practice: LLMs in Software Engineering and Software Architecture. Presented at 21st IEEE International Conference on Software Architecture (ICSA 2024): 3rd International Workshop on Software Architecture and Machine Learning, Hyderabad, India

Large Language Models (LLMs) are finding their way into Software Engineering by assisting with tasks such as code generation. Furthermore, LLMs might have a potential to perform even more complex tasks, such as suggesting architectural design. Howeve... Read More about State of Practice: LLMs in Software Engineering and Software Architecture.

Investigating Markers and Drivers of Gender Bias in Machine Translations (2024)
Presentation / Conference Contribution
Barclay, P., & Sami, A. (2024, March). Investigating Markers and Drivers of Gender Bias in Machine Translations. Presented at IEEE International Conference on Software Analysis, Evolution and Reengineering, Rovaniemi, Finland

Implicit gender bias in Large Language Models (LLMs) is a well-documented problem, and implications of gender introduced into automatic translations can perpetuate real-world biases. However, some LLMs use heuristics or post-processing to mask such b... Read More about Investigating Markers and Drivers of Gender Bias in Machine Translations.

A Deep Transfer Learning-Powered EDoS Detection Mechanism for 5G and Beyond Network Slicing (2024)
Presentation / Conference Contribution
Benzaïd, C., Taleb, T., Sami, A., & Hireche, O. (2023, December). A Deep Transfer Learning-Powered EDoS Detection Mechanism for 5G and Beyond Network Slicing. Presented at GLOBECOM 2023 - 2023 IEEE Global Communications Conference, Kuala Lumpur, Malaysia

Network slicing is recognized as a key enabler for 5G and beyond (B5G) services. However, its dynamic nature and the growing sophistication of DDoS attacks put it at risk of Economical Denial of Sustainability (EDoS) attack, causing economic losses t... Read More about A Deep Transfer Learning-Powered EDoS Detection Mechanism for 5G and Beyond Network Slicing.

A case study of fairness in generated images of Large Language Models for Software Engineering tasks (2023)
Presentation / Conference Contribution
Sami, M., Sami, A., & Barclay, P. (2023, October). A case study of fairness in generated images of Large Language Models for Software Engineering tasks. Presented at 2023 IEEE International Conference on Software Maintenance and Evolution (ICSME), Bogotá, Colombia

Bias in Large Language Models (LLMs) has significant implications. Since they have revolutionized content creation on the web, they can lead to more unfair outcomes, lack of inclusivity, reinforcement of stereotypes and ethical and legal concerns. No... Read More about A case study of fairness in generated images of Large Language Models for Software Engineering tasks.

Which bugs are missed in code reviews: an empirical study on SmartSHARK dataset (2022)
Presentation / Conference Contribution
Khoshnoud, F., Nasab, A. R., Toudeji, Z., & Sami, A. (2022, May). Which bugs are missed in code reviews: an empirical study on SmartSHARK dataset. Presented at MSR '22: 19th International Conference on Mining Software Repositories, Pittsburgh, US

In pull-based development systems, code reviews and pull request comments play important roles in improving code quality. In such systems, reviewers attempt to carefully check a piece of code by different unit tests. Unfortunately, sometimes they mis... Read More about Which bugs are missed in code reviews: an empirical study on SmartSHARK dataset.

Characterization and Prediction of Questions without Accepted Answers on Stack Overflow (2021)
Presentation / Conference Contribution
Yazdaninia, M., Lo, D., & Sami, A. (2021, May). Characterization and Prediction of Questions without Accepted Answers on Stack Overflow. Presented at 2021 IEEE/ACM 29th International Conference on Program Comprehension (ICPC), Madrid, Spain

A fast and effective approach to obtain information regarding software development problems is to search them to find similar solved problems or post questions on community question answering (CQA) websites. Solving coding problems in a short time is... Read More about Characterization and Prediction of Questions without Accepted Answers on Stack Overflow.

An Empirical Study of C++ Vulnerabilities in Crowd-Sourced Code Examples (2021)
Presentation / Conference Contribution
Verdi, M., Sami, A., Akhondali, J., Khomh, F., Uddin, G., & Karami Motlagh, A. (2021, May). An Empirical Study of C++ Vulnerabilities in Crowd-Sourced Code Examples. Presented at 43rd International Conference on Software Engineering, Online

Software developers share programming solutions in Q&A sites like Stack Overflow, Stack Exchange, Android forum, and so on. The reuse of crowd-sourced code snippets can facilitate rapid prototyping. However, recent research shows that the shared code... Read More about An Empirical Study of C++ Vulnerabilities in Crowd-Sourced Code Examples.

How Do Users Answer MATLAB Questions on Q&A Sites? A Case Study on Stack Overflow and MathWorks (2021)
Presentation / Conference Contribution
Naghashzadeh, M., Haghshenas, A., Sami, A., & Lo, D. (2021, March). How Do Users Answer MATLAB Questions on Q&A Sites? A Case Study on Stack Overflow and MathWorks. Presented at 28th IEEE International Conference on Software Analysis, Evolution and Reengineering 2021 (SANER 2021), Honolulu, HI, USA

MATLAB is an engineering programming language with various toolboxes that has a dedicated Question and Answer (Q&A) platform on the MathWorks website, which is similar to Stack Overflow (SO). Moreover, some MATLAB users ask their questions on SO. Thi... Read More about How Do Users Answer MATLAB Questions on Q&A Sites? A Case Study on Stack Overflow and MathWorks.

Malware detection based on mining API calls (2010)
Presentation / Conference Contribution
Sami, A., Yadegari, B., Rahimi, H., Peiravian, N., Hashemi, S., & Hamze, A. (2010, March). Malware detection based on mining API calls. Presented at The 2010 ACM Symposium, Sierre, Switzerland

Financial loss due to malware nearly doubles every two years. For instance in 2006, malware caused near 33.5 Million GBP direct financial losses only to member organizations of banks in UK. Recent malware cannot be detected by traditional signature b... Read More about Malware detection based on mining API calls.