20 citations · 41 across the 20 of their papers we have counts for
21 papers
Adaptive Code Revision Attacks on AI Pull Request Reviewers
Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova +1
Pull-request review protects software before new code reaches users, helping prevent vulnerabilities that could expose users to attacks. AI agents increasingly perform these review…
COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation
Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova +3
Code generation systems make each LLM call with a model, a prompt, and decoding settings. However, existing optimization methods usually tune only part of these choices or use one…
An Empirical Study of Downstream Adaptation for Agent Skills
Xinjian Wu, Jingzhi Gong, Gunel Jahangirova +2
As Large Language Model (LLM) agents become integral to modern software systems, ``skills'' have emerged as a novel unit of software reuse, enabling developers to package workflows…
How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study
Xinjian Wu, Jingzhi Gong, Gunel Jahangirova +1
Retrieval-augmented generation (RAG) pipelines for code completion rely on chunking to segment source files into retrievable units, yet chunking strategies are typically adopted wi…
Benchmarking and Evaluating VLMs for Software Architecture Diagram Understanding
Shuyin Ouyang, Jie M. Zhang, Jingzhi Gong +7
Software architecture diagrams are important design artifacts for communicating system structure, behavior, and data organization throughout the software development lifecycle. Alt…
LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops
Ravin Ravi, Dylan Bradshaw, Stefano Ruberto +2
Large Language Models (LLMs) are showing remarkable performance in generating source code, yet the generated code often has issues like compilation errors or incorrect code. Resear…
Revisiting "Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion": A Critical Review and Implications on DNN Coverage Testing
Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova +2
We present a critical review of Neural Coverage (NLC), a state-of-the-art DNN coverage criterion by Yuan et al. at ICSE 2023. While NLC proposes to satisfy eight design requirement…
Understanding LLM-Driven Test Oracle Generation
Adam Bodicoat, Gunel Jahangirova, Valerio Terragni
Automated unit test generation aims to improve software quality while reducing the time and effort required for creating tests manually. However, existing techniques primarily gene…
Fault Localisation and Repair for DL Systems: An Empirical Study with LLMs
Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova +2
Numerous Fault Localisation (FL) and repair techniques have been proposed to address faults in Deep Learning (DL) models. However, their effectiveness in practical applications rem…
Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development
Kuen Sum Cheung, Mayuri Kaul, Gunel Jahangirova +2
Large Language Models (LLM) have significantly transformed various domains, including software development. These models assist programmers in generating code, potentially increasi…
A Taxonomy of Real Faults in Hybrid Quantum-Classical Architectures
Avner Bensoussan, Gunel Jahangirova, Mohammad Reza Mousavi
With the popularity of Hybrid Quantum-Classical architectures, particularly noisy intermediate-scale quantum (NISQ) architectures, comes the need for quality assurance methods tail…
MuFF: Stable and Sensitive Post-training Mutation Testing for Deep Learning
Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova +2
Rapid adoptions of Deep Learning (DL) in a broad range of fields led to the development of specialised testing techniques for DL systems, including DL mutation testing. However, ex…
Real Faults in Deep Learning Fault Benchmarks: How Real Are They?
Gunel Jahangirova, Nargiz Humbatova, Jinhan Kim +2
As the adoption of Deep Learning (DL) systems continues to rise, an increasing number of approaches are being proposed to test these systems, localise faults within them, and repai…
An Empirical Study of Fault Localisation Techniques for Deep Learning
Nargiz Humbatova, Jinhan Kim, Gunel Jahangirova +2
With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Sever…
muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults
Deepak-George Thomas, Matteo Biagiola, Nargiz Humbatova +4
Reinforcement Learning (RL) is increasingly adopted to train agents that can deal with complex sequential tasks, such as driving an autonomous vehicle or controlling a humanoid rob…
GenMorph: Automatically Generating Metamorphic Relations via Genetic Programming
Jon Ayerdi, Valerio Terragni, Gunel Jahangirova +2
Metamorphic testing is a popular approach that aims to alleviate the oracle problem in software testing. At the core of this approach are Metamorphic Relations (MRs), specifying pr…
Repairing DNN Architecture: Are We There Yet?
Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova +2
As Deep Neural Networks (DNNs) are rapidly being adopted within large software systems, software developers are increasingly required to design, train, and deploy such models into…
DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score
Vincenzo Riccio, Nargiz Humbatova, Gunel Jahangirova +1
Deep Learning (DL) components are routinely integrated into software systems that need to perform complex tasks such as image or natural language processing. The adequacy of the te…
GAssert: A Fully Automated Tool to Improve Assertion Oracles
Valerio Terragni, Gunel Jahangirova, Paolo Tonella +1
This demo presents the implementation and usage details of GASSERT, the first tool to automatically improve assertion oracles. Assertion oracles are executable boolean expressions…
An Empirical Study on Failed Error Propagation in Java Programs with Real Faults
Gunel Jahangirova, David Clark, Mark Harman +1
During testing, developers can place oracles externally or internally with respect to a method. Given a faulty execution state, i.e., one that differs from the expected one, an ora…
Taxonomy of Real Faults in Deep Learning Systems
Nargiz Humbatova, Gunel Jahangirova, Gabriele Bavota +3
The growing application of deep neural networks in safety-critical domains makes the analysis of faults that occur in such systems of enormous importance. In this paper we introduc…