109 citations · 238 across the 52 of their papers we have counts for
56 papers
Hardware-Aware Conditional Code in Android Apps
Marco Alecci, Jordan Samhi, Li Li +2
Android OS runs on a highly diverse set of devices, spanning entry-level phones and flagships with substantially different hardware characteristics, including memory capacity, proc…
LëtzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents
Omar El Bachyr, Fred Philippy, Laura Maria Bernardy +3
Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-lingual, low-resource settings…
Semantic Drift in Bug Resolution: How Behavioral Signals Propagate from Reports to Tests and Patches
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang +7
Desc2Fix is a framework for measuring semantic alignment between bug reports, triggering tests, and developer-written fixes. Alignment is operationalized through structured behavio…
Benchmarking Face Recognition without Real Faces
Paweł Borsukiewicz, Daniele Lunghi, Wendkûuni C. Ouédraogo +2
Synthetic face datasets have become effective enough to train face recognition models with accuracy rivaling that of models trained on real photographs. This progress sidesteps the…
Humanizing Automatically Generated Unit Test Suites with LLM-Based Refactoring
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang +7
Search-based test generation tools such as EvoSuite produce compilable and high-coverage unit tests at scale, but their suites are often hard to read and maintain. LLMs can generat…
Evaluating LLMs for Obfuscation Detection and Classification in Android Apps
Luca Ferrari, Marco Alecci, Jordan Samhi +4
Android applications (apps) developers increasingly rely on code obfuscation techniques to hinder reverse engineering and protect intellectual property. However, obfuscation also r…
Empirical Study for Structured Output Control in LLMs for Software Engineering
Yewei Song, Prateek Rajput, Tiezhu Sun +3
LLM-generated outputs in software engineering rarely exist in isolation. They must plug into toolchains, APIs, and data pipelines that impose strict, often organization-specific st…
GapFuzz: Cross-Plane Divergence Fuzzing for Distributed SDN Controllers
Moustapha Awwalou Diouf, Samuel Ouya, Jacques Klein +1
Distributed Software-Defined Networking (SDN) clusters replicate flow state asynchronously between a master node and its backups, leaving a window during which two backup nodes can…
Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish
Fred Philippy, Siwen Guo, Jacques Klein +1
Cross-lingual transfer has become a central paradigm for extending natural language processing (NLP) technologies to low-resource languages. By leveraging supervision from high-res…
Evaluating Large Language Models in detecting Secrets in Android Apps
Marco Alecci, Jordan Samhi, Tegawendé F. Bissyandé +1
Mobile apps often embed authentication secrets, such as API keys, tokens, and client IDs, to integrate with cloud services. However, developers often hardcode these credentials int…
Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise
Paweł Borsukiewicz, Fadi Boutros, Iyiola E. Olatunji +4
The deployment of facial recognition systems has created an ethical dilemma: achieving high accuracy requires massive datasets of real faces collected without consent, leading to d…
Human-Aligned Code Readability Assessment with Large Language Models
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang +6
Code readability is crucial for software comprehension and maintenance, yet difficult to assess at scale. Traditional static metrics often fail to capture the subjective, context-s…
LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish
Fred Philippy, Laura Bernardy, Siwen Guo +2
Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human prompts. However, low-resource languages…
Explainable AI for Analyzing Person-Specific Patterns in Facial Recognition Tasks
Paweł Jakub Borsukiewicz, Jordan Samhi, Jacques Klein +1
The proliferation of facial recognition systems presents major privacy risks, driving the need for effective countermeasures. Current adversarial techniques apply generalized metho…
Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study
Serge Lionel Nikiema, Jordan Samhi, Micheline Bénédicte Moumoula +4
This research addresses a fundamental question in AI: whether large language models truly understand concepts or simply recognize patterns. The authors propose bidirectional reason…
MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs
Tiezhu Sun, Marco Alecci, Aleksandr Pilgun +5
The rapid evolution of Android malware poses significant challenges to the maintenance and security of mobile applications (apps). Traditional detection techniques often struggle t…
MT4DP: Data Poisoning Attack Detection for DL-based Code Search Models via Metamorphic Testing
Gong Chen, Wenjie Liu, Xiaoyuan Xie +3
Recently, several studies have indicated that data poisoning attacks pose a severe security threat to deep learning-based (DL-based) code search models. Attackers inject carefully…
Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning
Xunzhu Tang, Jacques Klein, Tegawendé F. Bissyandé
Several closed-source LLMs have consistently outperformed open-source alternatives in program repair tasks, primarily due to their superior reasoning capabilities and extensive pre…
Beyond Surface Similarity: Evaluating LLM-Based Test Refactorings with Structural and Semantic Awareness
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang +5
Large Language Models (LLMs) are increasingly used to refactor unit tests, improving readability and structure while preserving behavior. Evaluating such refactorings, however, rem…
Rethinking Cognitive Complexity for Unit Tests: Toward a Readability-Aware Metric Grounded in Developer Perception
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang +5
Automatically generated unit tests-from search-based tools like EvoSuite or LLMs-vary significantly in structure and readability. Yet most evaluations rely on metrics like Cyclomat…
Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis
Albérick Euraste Djiré, Abdoul Kader Kaboré, Earl T. Barr +2
While Large Language Models (LLMs) achieve remarkable performance through training on massive datasets, they can exhibit concerning behaviors such as verbatim reproduction of train…
The Code Barrier: What LLMs Actually Understand?
Serge Lionel Nikiema, Jordan Samhi, Abdoul Kader Kaboré +2
Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engine…
Enhancing Small Language Models for Cross-Lingual Generalized Zero-Shot Classification with Soft Prompt Tuning
Fred Philippy, Siwen Guo, Cedric Lothritz +2
In NLP, Zero-Shot Classification (ZSC) has become essential for enabling models to classify text into categories unseen during training, particularly in low-resource languages and…
Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?
Yewei Song, Lujun Li, Cedric Lothritz +6
Low-resource languages (LRLs) lack sufficient linguistic resources and are underrepresented in benchmark datasets, resulting in persistently lower translation quality than high-res…