Publications (284)
ARTICLE
Towards Innovative Intelligent Cyber Defense Approach Based on Deceptive Security and Deep Learning Techniques
Saoudata Bougma, Didier Bassole, Pegdwindé Justin kouraogo, Sidwendluian Romaric Nana
In this paper, we propose a critical analysis of recent advances in cybersecurity, particularly the application of deep learning, cyber threat intelligence, and deceptive security. Building on this analysis, we introduce an integrated and innovative approach that combines the collection of attacker traces through deception systems (honeypots)(...)
Cybersecurity, Deceptive Security, Deep Learning, Real Time
ARTICLE
LongTest: Test Prioritization for Long Text Files
Xueqi Dang, Yinghua Li, Wendkuuni C. Ouedraogo, Maxime Cordy, Mike Papadakis, Jacques Klein, Tegawende F. Bissyande, Yves Le Traon
Text classification is a fundamental task in natural language processing (NLP) that involves assigning predefined labels to text files. While existing research has primarily focused on short texts (e.g., social media posts), the classification of long texts, such as legal documents and medical records, has gained increasing attention due to th(...)
Test input prioritization , deep neural network , labelling
COMMUNICATION
Evaluating LLM-Based Test Refactoring with a Behavior-Preserving Composite Metric
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang, Paweł Borsukiewicz, Xin Zhou, Anıl Koyuncu, Jacques Klein, David Lo, Tegawendé F. Bissyandé
Large Language Models (LLMs) are increasingly used to refactor automatically generated unit tests, which often achieve high coverage but suffer from poor readability and maintainability. Evaluating such refactorings remains challenging, as existing metrics either penalize beneficial edits or overlook readability. We introduce CTSES, a composit(...)
GPT-4o, Mistral-Large-2407, across, Defects4J, SF110
ARTICLE
Toward an Operational Intrusion Detection and Prevention System for SDN-IoT: A Cascaded Deep Learning Approach with Automatic Mitigation
Yacouba OUATTARA,Yaya TRAORE, Abdoul Razak TARPAGA
Abstract—The convergence of software-defined networking and the Internet of Things widens the attack surface of connected networks
and calls for defenses able to detect attacks at the controller's vantage point and to block them there. Earlier work compared deep
architectures for denial-of-service attack detection and opened two perspectives(...)
Cybersecurity; deep learning; intrusion detection and prevention system (IDPS); software-defined networking (SDN); Internet of Things (IoT); mitigation; cascaded classification; ASEADOS-SDN-IoT.
COMMUNICATION
Replacing Training with Reasoning: Reinterpreting Classic ML Pipelines with LLMs
Marco Alecci, Jordan Samhi, Tegawendé F. Bissyandé, Jacques Klein
Large Language Models (LLMs) are increasingly used in software engineering tasks due to their strong performance across diverse applications. In this paper, we ask a fundamental and novel question: To what extent can LLMs replace traditional machine learning pipelines that rely on labeled data, feature engineering, and retraining?
Our intuiti(...)
llms, METEOR, ROUGE
ARTICLE
IoT Systems Security Enhanced Based on Federated Learning and Blockchain Technology
Manegawindin Léonard Sawadogo, Didier Bassole, Boureima Zerbo
IoT systems have become very popular in recent years and are present in all areas. They collect and process data that is often sensitive and confidential, making them targets for increasingly sophisticated and frequent attacks. In the field of IoT cybersecurity, Federated Learning and Blockchain Technology are showing promising results. In thi(...)
Federated Learning, IoT, Cybersecurity, Blockchain
ARTICLE
On the Diffusion of Test Smells in LLM-Generated Unit Tests
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang, Xunzhu Tang, Anil Koyuncu, Jacques Klein, David Lo, Tegawendé F. Bissyandé
LLMs promise to transform Java unit test generation from a manual burden into an automated solution. Yet, beyond metrics such as compilability or coverage, the quality of LLM-generated Java tests (particularly their susceptibility to test smells, design flaws that undermine readability and maintainability) remains insufficiently understood. Re(...)
GPT-3.5, GPT-4, Mistral 7B, Mixtral 8×7B
ARTICLE
Enhanced Private key Synchronization Mechanism Security in Passkeys System Based on Elliptic Curve Diffie-Hellman and Zero-Knowledge Proofs
Assane Ilboudo, Didier Bassole, Désiré Guel
Based on asymmetric cryptography, Passkeys Systems are a secure authentication method that can serve as an alternative to traditional authentication methods, such as usernames and passwords. In this paper, we propose a secure approach to enhance private key synchronization mechanisms in passkeys systems. Our secure service is based on Elliptic(...)
Elliptic Curve Diffie-Hellman, Zero-Knowledge Proofs, Informal Analysis, Formal Analysis, Security
ARTICLE
Formalizing PI Planning in Scaled Agile with Model-Driven Engineering: A Metamodel and Framework for Strategic Alignment
Flavien Somda ; Désiré Guel ; Kisito Kabore
Program Increment (PI) Planning is a critical synchronization event in scaled Agile methodologies, yet remains largely informal, with limited analytical rigor or strategic alignment. This paper introduces a formal metamodel and a model-driven framework to support structured PI Planning in large-scale software development. Our metamodel capture(...)
Program Increment Planning, Agile Methodologies, Metamodel, Model-Driven Engineering, Im pact Analysis, Modeling Framework
ARTICLE
Public key Integrity Verification and Restoration Approach in Passkeys Based on Blockchain and Security Analysis Under Dolev-Yao Model Using ProVerif
Ilboudo Assane, Didier Bassolé, Guel Désiré
This work proposes a decentralized mechanism for the verification and restoration of public keys in passkey-based authentication systems. The model relies on a synergistic integration of Blockchain and the distributed file system IPFS, aiming to eliminate dependence on a centralized trusted third party and to enhance the resilience of public k(...)
Passkey Sytem , Blockchain , Security Analysis, Dolev–Yao
ARTICLE
MITRE-CAPE-2026: A Novel Dataset for Cyber Attackers Profiling Enhancement
Saoudata Bougma, Didier Bassolé, Sidwendluian Romaric Nana, P. Justin Kouraogo
Experimental cybersecurity research has traditionally relied on using datasets to train intrusion detection systems (IDS). However, current solutions suffer from outdated reference data and an event-centric approach limited to binary traffic classification or attack type identification. This article argues that threat anticipation requires a p(...)
Cybersecurity , Dataset , Attacker Profiling , BERT Model
COMMUNICATION
GeoTwins: Uncovering Hidden Geographic Disparities in Android Apps
Marco Alecci, Pedro Jesús Ruiz Jiménez, Jordan Samhi, Tegawendé F. Bissyandé, Jacques Klein
While mobile app evolution over time has been extensively studied, geographical variation in app behavior remains largely unexplored. This paper presents a large-scale study of location-based Android app differentiation, uncovering two underexplored phenomena with significant security and fairness implications.
First, we introduce the concept(...)
permissions, libraries, or privacy
ARTICLE
LPWAN Localization via RSSI/SNR Fingerprinting and Lightweight Machine Learning
Désiré Guel, Flavien Hervé Somda, P. Justin Kouraogo, Boureima Zerbo and Oumarou Sié
Accurate geolocation for low-power wide-area (LPWAN) devices is desirable when GNSS is unavailable or too energy-expensive, yet RSSI-/TDoA-based approaches are often fragile under channel variability, collisions and cross-device heterogeneity. We address this gap with a reproducible, tabular pipeline that maps LoRa RSSI/SNR/ToA and PHY metadat(...)
LPWAN, LoRA, Localization, Fingerprinting, RSSI, SNR, IoT, Machine Learning
ARTICLE
Innovative and Secure Private Key Synchronization Mechanism Between Devices Using Peer-to-Peer Approach in Passkeys System
Assane ILBOUDO, Didier BASSOLE, Désiré GUEL
Passkeys are a passwordless authentication method that is increasingly being adopted. Based on asymmetric cryptography, they offer a secure and promising alternative to traditional passwords. In this paper, we propose a new secure approach for passkey synchronization based on a Peer-to-Peer mechanism between devices. Our secure services integr(...)
Elliptic Curve Diffie-Hellman, Passkey system, Zero-Knowledge Proofs, Security
ARTICLE
TaskFlow: LLMs for Android Taint Specification
Marco Alecci, Jordan Samhi, Marc Miltenberger, Steven Arzt, Tegawendé F. Bissyandé, Jacques Klein
Taint analysis is a widely used technique to analyze Android apps, enabling the tracking of data flow within an app. A key step consists in identifying which methods act as SOURCEs (i.e., where a data of interest originates) and SINKs (where data might be exposed). Existing approaches typically fall into two categories: ➀ Handcrafted lists, wh(...)
LPWAN, LoRa, Localization, Machine Learning, Fingerprinting, RSSI, SNR, IoT