no code implementations • 8 Nov 2023 • Thibault Simonetto, Salah Ghamizi, Antoine Desjardins, Maxime Cordy, Yves Le Traon
State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings.
no code implementations • 29 Jul 2023 • Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Wei Ma, Mike Papadakis, Yves Le Traon
Testing deep learning-based systems is crucial but challenging due to the required time and labor for labeling collected raw data.
no code implementations • 27 Jul 2023 • Yuejun Guo, Seifeddine Bettaieb, Qiang Hu, Yves Le Traon, Qiang Tang
Representing source code in a generic input format is crucial to automate software engineering tasks, e. g., applying machine learning algorithms to extract information.
no code implementations • 10 May 2023 • Jie Zhang, Wei Ma, Qiang Hu, Shangqing Liu, Xiaofei Xie, Yves Le Traon, Yang Liu
Furthermore, the perturbation of adversarial examples introduced by RNNS is smaller compared to the baselines in terms of the number of replaced variables and the change in variable length.
no code implementations • 8 May 2023 • Sai Sathiesh Rajan, Ezekiel Soremekun, Yves Le Traon, Sudipta Chattopadhyay
This work addresses how to validate group fairness in image recognition software.
1 code implementation • 5 Apr 2023 • Martin Gubri, Maxime Cordy, Yves Le Traon
A common hypothesis to explain this is that deep neural networks (DNNs) first learn robust features, which are more generic, thus a better surrogate.
no code implementations • 13 Mar 2023 • Zeming Dong, Qiang Hu, Yuejun Guo, Zhenya Zhang, Maxime Cordy, Mike Papadakis, Yves Le Traon, Jianjun Zhao
The next era of program understanding is being propelled by the use of machine learning to solve software problems.
1 code implementation • 6 Feb 2023 • Salah Ghamizi, Jingfeng Zhang, Maxime Cordy, Mike Papadakis, Masashi Sugiyama, Yves Le Traon
While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models.
no code implementations • 15 Dec 2022 • Salah Ghamizi, Maxime Cordy, Michail Papadakis, Yves Le Traon
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural Networks.
1 code implementation • 6 Oct 2022 • Zeming Dong, Qiang Hu, Yuejun Guo, Maxime Cordy, Mike Papadakis, Zhenya Zhang, Yves Le Traon, Jianjun Zhao
Data augmentation has been a popular approach to supplement training data in domains such as computer vision and NLP.
no code implementations • 6 Oct 2022 • Zeming Dong, Qiang Hu, Zhenya Zhang, Yuejun Guo, Maxime Cordy, Mike Papadakis, Yves Le Traon, Jianjun Zhao
Graph neural network (GNN)-based graph learning has been popular in natural language and programming language processing, particularly in text and source code classification.
1 code implementation • 26 Jul 2022 • Martin Gubri, Maxime Cordy, Mike Papadakis, Yves Le Traon, Koushik Sen
We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks.
1 code implementation • 22 Jul 2022 • Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Lei Ma, Mike Papadakis, Yves Le Traon
Recent studies show that test selection for DNN is a promising direction that tackles this issue by selecting minimal representative data to label and using these data to assess the model.
2 code implementations • 11 Jun 2022 • Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Lei Ma, Mike Papadakis, Yves Le Traon
Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation.
1 code implementation • 8 Apr 2022 • Qiang Hu, Yuejun Guo, Maxime Cordy, Xiaofei Xie, Mike Papadakis, Yves Le Traon
Applying deep learning to science is a new trend in recent years which leads DL engineering to become an important problem.
1 code implementation • 8 Apr 2022 • Qiang Hu, Yuejun Guo, Maxime Cordy, Xiaofei Xie, Wei Ma, Mike Papadakis, Yves Le Traon
The results reveal that 1) data with distribution shifts happen more disagreements than without.
1 code implementation • 7 Feb 2022 • Salijona Dyrmishi, Salah Ghamizi, Thibault Simonetto, Yves Le Traon, Maxime Cordy
While the literature on security attacks and defense of Machine Learning (ML) systems mostly focuses on unrealistic adversarial examples, recent research has raised concern about the under-explored field of realistic adversarial attacks and their implications on the robustness of real-world systems.
no code implementations • 5 Dec 2021 • Yuejun Guo, Qiang Hu, Maxime Cordy, Mike Papadakis, Yves Le Traon
Our acquisition function -- named density-based robust sampling with entropy (DRE) -- outperforms the other acquisition functions (including random) in terms of robustness by up to 24. 40\% (3. 84\% than random particularly), while remaining competitive on accuracy.
no code implementations • 2 Dec 2021 • Thibault Simonetto, Salijona Dyrmishi, Salah Ghamizi, Maxime Cordy, Yves Le Traon
We propose a unified framework to generate feasible adversarial examples that satisfy given domain constraints.
1 code implementation • 26 Oct 2021 • Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks.
no code implementations • 27 Sep 2021 • Yuejun Guo, Qiang Hu, Maxime Cordy, Michail Papadakis, Yves Le Traon
In this paper, we propose MUTEN, a low-cost method to improve the success rate of well-known attacks against gradient-masking models.
1 code implementation • 21 Dec 2020 • Aayush Garg, Renzo Degiovanni, Matthieu Jimenez, Maxime Cordy, Mike Papadakis, Yves Le Traon
To tackle these issues, we propose TROVON, a technique that learns from known vulnerable components rather than from vulnerable and non-vulnerable components, as typically performed.
Machine Translation Cryptography and Security Software Engineering
no code implementations • 14 Dec 2020 • Adriano Franci, Maxime Cordy, Martin Gubri, Mike Papadakis, Yves Le Traon
Graph-based Semi-Supervised Learning (GSSL) is a practical solution to learn from a limited amount of labelled data together with a vast amount of unlabelled data.
no code implementations • 11 Dec 2020 • Ahmed Khanfir, Anil Koyuncu, Mike Papadakis, Maxime Cordy, Tegawendé F. Bissyandé, Jacques Klein, Yves Le Traon
It remains indeed challenging to inject few but realistic faults that target a particular functionality in a program.
Fault Detection Program Repair +2 Software Engineering
1 code implementation • 10 Nov 2020 • Martin Gubri, Maxime Cordy, Mike Papadakis, Yves Le Traon, Koushik Sen
An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity.
no code implementations • 14 Nov 2019 • Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon
The key idea of our method is to use deep neural networks for image classification and adversarial attacks to embed secret information within images.
2 code implementations • 12 Jul 2019 • Anil Koyuncu, Kui Liu, Tegawendé F. Bissyandé, Dongsun Kim, Martin Monperrus, Jacques Klein, Yves Le Traon
Towards increasing the adoption of patch generation tools by practitioners, we investigate a new repair pipeline, iFixR, driven by bug reports: (1) bug reports are fed to an IR-based fault localizer; (2) patches are generated from fix patterns and validated via regression testing; (3) a prioritized list of generated patches is proposed to developers.
Software Engineering
no code implementations • 30 Apr 2019 • Wei Ma, Mike Papadakis, Anestis Tsakmalis, Maxime Cordy, Yves Le Traon
This raises the question of how we can automatically select candidate test data to test deep learning models.
1 code implementation • 9 Apr 2019 • Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon
First, we model the variability of DNN architectures with a Feature Model (FM) that generalizes over existing architectures.
no code implementations • 10 Jun 2016 • Daoyuan Li, Li Li, Dongsun Kim, Tegawendé F. Bissyandé, David Lo, Yves Le Traon
One single code change can significantly influence a wide range of software systems and their users.
Software Engineering
1 code implementation • 11 Jan 2016 • Thomas Laurent, Anthony Ventresque, Mike Papadakis, Christopher Henard, Yves Le Traon
We therefore examine how effective are the mutants of a popular mutation testing tool, named PIT, compared to comprehensive ones, as drawn from the literature and personal experience.
Software Engineering
no code implementations • 18 Feb 2014 • Donia El Kateb, François Fouquet, Johann Bourcier, Yves Le Traon
In the last years, multi-objective evolutionary algorithms (MOEA) have been applied to different software engineering problems where many conflicting objectives have to be optimized simultaneously.