Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 15 of 15 for “"AI-Generated Code"”.
-
Energy Efficiency of AI Generated Code
Recent advances in AI have created new prospects for improving software development, particularly through the usage of Large Language Models (LLMs) for code generation. The increasing integration of code generation models into software development has heightened the need to evaluate not only the …
-
Security and Authenticity of AI-generated code
… of security and plagiarism in the context of AI-generated code is a critical theme through- out this study. While our research primarily focuses on evaluating the security aspects of AI-generated code, it is imperative to recognize the interconnectedness of security and plagiarism concerns. On …
-
Issues in Detection of AI-Generated Source Code
AI coding assistants hold the promise of revolutionizing software development, but they also introduce new risks. The underlying large language models (LLMs) can generate faulty or insecure code either unintentionally or through malicious attacks. Additionally, there's a potential for AI assistants …
-
Security weaknesses in AI-generated code : a comparative analysis across models and programming languages : a thesis presented in partial fulfilment of the requirements for the degree of Master of Information Sciences in Software Engineering at Massey University, Palmerston North, New Zealand
The security of AI-generated code remains a major challenge for its widespread adoption. Code generation models have demonstrated strong performance on functional benchmarks. However, their outputs frequently contain bugs and security weaknesses that reduce their reliability in real-world settings. …
-
Authorship Attribution of AI-generated Codes
The field of code authorship attribution focuses on identifying the author(s) of source code written in a specific programming language. Various methods, including manual crafting, automated crafting, and deep learning-generated features, have been developed for this task. These techniques leverage …
-
The Role of AI in Software Development: Industry Practices, Security Implications, and Developer Perceptions
The rise of large language models (LLMs) and AI tools like ChatGPT is transforming software development by enhancing workflows through code generation, autocompletion, and debugging. While these tools promise increased productivity, their integration raises concerns about security, privacy, and …
-
AI in the Loop: How AI Affects Roles, Collaboration, and Trust in Agile Software Development
… collaborative practices, and trust in AI-generated code within agile and DevOps team environments. A mixed-methods approach is used, combining semi-structured interviews with eleven developers across a varying range of company sizes, sectors, roles, and experience levels, and a …
-
Towards modeling and improving human-centered code review
Tool-based code review has been an established software engineering practice for at least a decade. However, while software development environments have improved significantly during this time with advanced features for code comprehension, refactoring, and AI support, code review tools have …
-
Evaluating the Use of Generative AI in Software Development Proposing a Tentative Framework
Artificial intelligence (AI), especially generative AI (GenAI), has significantly impacted society and industries, driven by its ability to generate original content from data patterns. Recent advancements, like ChatGPT, have highlighted GenAI's potential to boost productivity in software …
-
Classifying Code as Human Authored or GPT-4 Generated
Artificial intelligence (AI) assistants such as GitHub Copilot and ChatGPT, built on large language models like GPT-4, are revolutionizing how programming tasks are performed, raising questions about whether generative AI models author code. Such questions are of particular interest to educators, …
-
Interaction and Cognition in AI-Assisted Programming
… new technology. However, the rise of Generative AI is transforming how programming is learned and practiced. While AI can boost productivity by generating code from natural language descriptions, novice learners may over-rely on AI, creating cognitive debt. Learners may struggle to self-regulate …
-
Effects of Practice with Parsons' Problems: Confidence and Performance
While most traditional computer science programs maintain a heavy focus on developing new code from scratch to educate its students, the vast majority of industrial work centers on maintenance, fixing, and adding to pre-existing software systems. This work focuses on code that is typically …
-
Application of Large Language Models in Code Clone: Benchmarking, Evaluation and Detection
… grow increasingly complex, the detection of code clones has become vital for software maintenance and security analysis. Among the various types of clones, Type-4 or semantic clones (code fragments that perform the same function but differ syntactically) is difficult to detect due to their …
-
Statistical Methods for Performance Evaluation of Machine Learning and Artificial Intelligence Models
Artificial Intelligence (AI) and Machine Learning (ML) have revolutionized the field of statistics by introducing advanced data analysis methods for predictive modeling and decision- making. These technologies facilitate handling both structured and unstructured data with high accuracy and …
-
Usability Evaluation of LLM-Assisted Cross-Platform Migration
… language models are evaluated on whether the code they generate compiles and passes tests. Whether code is usable is a question that has received little attention so far. This thesis asks it in the context of cross-platform mHealth application migration. A sleep-tracking application (React …