Publications (267)
ARTICLE
You Don’t Have to Say Where to Edit! jLED—Joint Learning to Localize and Edit Source Code
Weiguo Pian, Yinghua Li, Haoye Tian, Tiezhu Sun, Yewei Song, Xunzhu Tang, Andrew Habib, Jacques Klein, Tegawendé F. Bissyandé
Learning to edit code automatically is becoming more and more feasible. Thanks to recent advances in Neural Machine Translation (NMT), various case studies are being investigated where patches are automatically produced and assessed either automatically (using test suites) or by developers themselves. An appealing setting remains when the deve(...)
Learning
ARTICLE
Advancements in Deep Learning for Malaria Detection: A Comprehensive Overview
Kiswendsida Kisito Kabore and Desire Guel and Flavien Herve Somda
Malaria remains a critical global health issue, with millions of cases reported annually, particularly in resource-limited regions. Timely and accurate diagnosis is vital to ensure effective treatment, reduce complications, and control transmission. Conventional diagnostic methods, including microscopy and Rapid Diagnostic Tests (RDTs), face c(...)
Malaria detection, Deep Learning, Convolutional Neural Networks (CNN), Medical Imaging, Automated diagnostics
THèSE
Analyse des réseaux sociaux pour l’extraction d’événements et de données qualitatives pour la veille des épidémies basée sur les ontologies : Application à la veille de la méningite au Burkina Faso
WEND-PANGA RÉGIS CÉDRIC BÉRÉ
Cette thèse aborde l’amélioration de la détection précoce des épidémies de méningite en Afrique subsaharienne par l’utilisation des réseaux sociaux, en complément des systèmes de surveillance sanitaire traditionnels. Face au manque d’outils de collecte en temps réel, elle propose une approche combinant ingénierie des ontologies et analyse des(...)
Infomédiologie, Ontologie, Méningite, Analyse des réseaux sociaux, Surveillance épidémiologique
ARTICLE
AudioTest: Prioritizing Audio Test Cases
Yinghua Li, Xueqi Dang, Wendkûuni C. Ouédraogo, Jacques Klein, Tegawendé F. Bissyandé
Audio classification systems, powered by deep neural networks (DNNs), are integral to various applications that impact daily lives, like voice-activated assistants. Ensuring the accuracy of these systems is crucial since inaccuracies can lead to significant security issues and user mistrust. However, testing audio classifiers presents a signif(...)
Prioritizing Audio Test Cases
ARTICLE
The Struggles of LLMs in Cross-Lingual Code Clone Detection
Micheline Bénédicte Moumoula, Abdoul Kader Kaboré, Jacques Klein, Tegawendé F. Bissyandé
With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing various promising approaches. Inspired by the significant advances in machine learning in recent years, par(...)
LLMs
ARTICLE
Assessing Robustness and Resistance to Attacks of an Authentication System Based on OpenID Connect Protocol and Ethereum Blockchain
Ilboudo Assane; Bassole Didier; Kouraogo Justin Pegdwindé; Koala Gouayon; Sie Oumarou
In this paper, we assess the robustness and resistance against various types of attacks of a multi-factor authentication mechanism that we have proposed. It is a mechanism based on the OpenID Connect protocol and utilizes the Ethereum blockchain. Robustness was evaluated by conducting appropriate security tests using AVISPA and Scyther protoco(...)
Single Sign-On, Robustness, Ethereum Blockchain, OpenID Connect
ARTICLE
Vulnerabilities in infrastructure as code: what, how many, and who?
Aicha War, Alioune Diallo, Andrew Habib, Jacques Klein, Tegawendé F. Bissyandé
Infrastructure as Code (IaC) is a pivotal approach for deploying and managing IT systems and services using scripts, offering flexibility and numerous benefits. However, the presence of security flaws in IaC scripts can have severe consequences, as exemplified by the recurring exploits of Cloud Web Services. Recent studies in the literature ha(...)
Vulnerabilities
ARTICLE
Détection de communautés dans les graphes de connaissance d'activités
Marthe Désirée Olivia HABACK , Serge SONFACK SOUNCHIO , Orlane SONKENG TSAFACK , Halguièta NASSA TRAWINA , Ho Tuong Vinh
La gestion des connaissances produites au cours des activités au sein des organisations joue un rôle important dans leur développement et leur succès. La formalisation de ces connaissances sous forme de graphe de connaissance d’activités (Activity Knowledge Graph : AKG) permet de représenter et de réutiliser ces connaissances pour résoudre des(...)
Graphe de connaissance, graphe de connaissance d’activité, détection de communauté, algorithme de Louvain
ARTICLE
How Are We Detecting Inconsistent Method Names? An Empirical Study from Code Review Perspective
Kisub Kim, Xin Zhou, Dongsun Kim, Julia Lawall, Kui Liu, Tegawende F. Bissyande, Jacques Klein, Jaekwon Lee, David Lo
Proper naming of methods can make program code easier to understand, and thus enhance software maintainability. Yet, developers may use inconsistent names due to poor communication or a lack of familiarity with conventions within the software development lifecycle. To address this issue, much research effort has been invested into building aut(...)
Inconsistent
ARTICLE
LLM for Mobile: An Initial Roadmap
Daihang Chen, Yonghui Liu, Mingyi Zhou, Yanjie Zhao, Haoyu Wang, Shuai Wang, Xiao Chen, Tegawendé F. Bissyandé, Jacques Klein, Li Li
When mobile meets LLMs, mobile app users deserve to have more intelligent usage experiences. For this to happen, we argue that there is a strong need to apply LLMs for the mobile ecosystem. We therefore provide a research roadmap for guiding our fellow researchers to achieve that as a whole. In this roadmap, we sum up six directions that we be(...)
LLM
ARTICLE
Just-in-Time Detection of Silent Security Patches
Xunzhu Tang, Kisub Kim, Saad Ezzini, Yewei Song, Haoye Tian, Jacques Klein, Tegawende Bissyande
Open-source code is pervasive. In this setting, embedded vulnerabilities are spreading to downstream software at an alarming rate. Although such vulnerabilities are generally identified and addressed rapidly, inconsistent maintenance policies can cause security patches to go unnoticed. Indeed, security patches can be silent, i.e., they do not(...)
Patches
ARTICLE
Performance of the Large Language Models in African rheumatology: a diagnostic test accuracy study of ChatGPT-4, Gemini, Copilot, and Claude artificial intelligence.
Yannick Laurent Tchenadoyo Bayala, Wendlassida Joelle Stéphanie Zabsonré/Tiendrebeogo, Dieu- Donné Ouedraogo , Fulgence Kaboré , Charles Sougué , Aristide Relwendé Yameogo , Wendlassida Martin Nacanabo , Ismael Ayouba Tinni, Aboubakar Ouedraogo and Yamyellé Enselme Zongo.
Background: Artificial intelligence (AI) tools, particularly Large Language Models (LLMs), are revolutionizing medical practice, including rheumatology. However, their diagnostic capabilities remain underexplored in the African context. To assess the diagnostic accuracy of ChatGPT-4, Gemini, Copilot, and Claude AI in rheumatology within an Afr(...)
Africa; Artificial intelligence; Diagnostic accuracy; Large Language Models; Rheumatology
ARTICLE
A large-scale LPWAN Architecture for Multimedia Data Collection in High-security Challenge Areas
OUATTARA Yacouba, PODA Pasteur et TRAORE Mamouta
The Internet of Things (IoT) is rapidly expanding, including in conflict zones where security is
critical. Sound signals used for intelligence in the Middle East, combined with Sahel challenges from poor
infrastructure, emphasize the need for better data collection. This paper proposes a secure IoT architecture
using Low Power Wide Area Net(...)
LPWAN, LoRaWAN, Architecture, Design, Terrorism, Steganography, Military.
ARTICLE
Temporal-Incremental Learning for Android Malware Detection
Tiezhu Sun, Nadia Daoudi, Weiguo Pian, Kisub Kim, Kevin Allix, Tegawendé F. Bissyandé, Jacques Klein
Malware classification is a specific and refined task within the broader malware detection problem. Effective classification aids in understanding attack techniques and developing robust defenses, ensuring application security and timely mitigation of software vulnerabilities. The dynamic nature of malware demands adaptive classification techn(...)
Android Malware
ARTICLE
Drop-in efficient self-attention approximation method
Damien François, Mathis Saillot, Jacques Klein, Tegawendé F. Bissyandé, Alexander Skupin
Transformers have achieved state-of-the-art performance in most common tasks to which they have been applied. Those achievements are attributed to the Self-Attention mechanism at their core. Self-Attention is understood to map the relationship between tokens of any given sequence. This exhaustive mapping incurs massive costs in memory and infe(...)
method