References of "Cordy, Maxime 50027892"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailFaster and Cheaper Energy Demand Forecasting at Scale
Bernier, Fabien UL; Jimenez, Matthieu UL; Cordy, Maxime UL et al

in Has it Trained Yet? Workshop at the Conference on Neural Information Processing Systems (2022, December 02)

Energy demand forecasting is one of the most challenging tasks for grids operators. Many approaches have been suggested over the years to tackle it. Yet, those still remain too expensive to train in terms ... [more ▼]

Energy demand forecasting is one of the most challenging tasks for grids operators. Many approaches have been suggested over the years to tackle it. Yet, those still remain too expensive to train in terms of both time and computational resources, hindering their adoption as customers behaviors are continuously evolving. We introduce Transplit, a new lightweight transformer-based model, which significantly decreases this cost by exploiting the seasonality property and learning typical days of power demand. We show that Transplit can be run efficiently on CPU and is several hundred times faster than state-of-the-art predictive models, while performing as well. [less ▲]

Detailed reference viewed: 29 (3 UL)
Full Text
Peer Reviewed
See detailGraphCode2Vec: generic code embedding via lexical and program dependence analyses
Ma, Wei UL; Zhao, Mengjie; Soremekun, Ezekiel UL et al

in Proceedings of the 19th International Conference on Mining Software Repositories (2022, May 22)

Code embedding is a keystone in the application of machine learn- ing on several Software Engineering (SE) tasks. To effectively support a plethora of SE tasks, the embedding needs to capture program ... [more ▼]

Code embedding is a keystone in the application of machine learn- ing on several Software Engineering (SE) tasks. To effectively support a plethora of SE tasks, the embedding needs to capture program syntax and semantics in a way that is generic. To this end, we propose the first self-supervised pre-training approach (called GraphCode2Vec) which produces task-agnostic embedding of lexical and program dependence features. GraphCode2Vec achieves this via a synergistic combination of code analysis and Graph Neural Networks. GraphCode2Vec is generic, it allows pre-training, and it is applicable to several SE downstream tasks. We evaluate the effectiveness of GraphCode2Vec on four (4) tasks (method name prediction, solution classification, mutation testing and overfitted patch classification), and compare it with four (4) similarly generic code embedding baselines (Code2Seq, Code2Vec, CodeBERT, Graph- CodeBERT) and seven (7) task-specific, learning-based methods. In particular, GraphCode2Vec is more effective than both generic and task-specific learning-based baselines. It is also complementary and comparable to GraphCodeBERT (a larger and more complex model). We also demonstrate through a probing and ablation study that GraphCode2Vec learns lexical and program dependence features and that self-supervised pre-training improves effectiveness. [less ▲]

Full Text
See detailTowards Generalizable Machine Learning for Chest X-ray Diagnosis with Multi-task learning
Ghamizi, Salah UL; Garcia Santa Cruz, Beatriz UL; Temple, Paul et al

E-print/Working paper (2022)

Clinicians use chest radiography (CXR) to diagnose common pathologies. Automated classification of these diseases can expedite analysis workflow, scale to growing numbers of patients and reduce healthcare ... [more ▼]

Clinicians use chest radiography (CXR) to diagnose common pathologies. Automated classification of these diseases can expedite analysis workflow, scale to growing numbers of patients and reduce healthcare costs. While research has produced classification models that perform well on a given dataset, the same models lack generalization on different datasets. This reduces confidence that these models can be reliably deployed across various clinical settings. We propose an approach based on multitask learning to improve model generalization. We demonstrate that learning a (main) pathology together with an auxiliary pathology can significantly impact generalization performance (between -10% and +15% AUC-ROC). A careful choice of auxiliary pathology even yields competitive performance with state-of-the-art models that rely on fine-tuning or ensemble learning, using between 6% and 34% of the training data that these models required. We, further, provide a method to determine what is the best auxiliary task to choose without access to the target dataset. Ultimately, our work makes a big step towards the creation of CXR diagnosis models applicable in the real world, through the evidence that multitask learning can drastically improve generalization. [less ▲]

Detailed reference viewed: 97 (15 UL)
Full Text
Peer Reviewed
See detailMulti-agent deep reinforcement learning based Predictive Maintenance on parallel machines
Ruiz Rodriguez, Marcelo Luis UL; Kubler, Sylvain UL; de Giorgio, Andrea et al

in Robotics and Computer-Integrated Manufacturing (2022)

In the context of Industry 4.0, companies understand the advantages of performing Predictive Maintenance (PdM). However, when moving towards PdM, several considerations must be carefully examined. First ... [more ▼]

In the context of Industry 4.0, companies understand the advantages of performing Predictive Maintenance (PdM). However, when moving towards PdM, several considerations must be carefully examined. First, they need to have a sufficient number of production machines and relative fault data to generate maintenance predictions. Second, they need to adopt the right maintenance approach, which, ideally, should self-adapt to the machinery, priorities of the organization, technician skills, but also to be able to deal with uncertainty. Reinforcement learning (RL) is envisioned as a key technique in this regard due to its inherent ability to learn by interacting through trials and errors, but very few RL-based maintenance frameworks have been proposed so far in the literature, or are limited in several respects. This paper proposes a new multi-agent approach that learns a maintenance policy performed by technicians, under the uncertainty of multiple machine failures. This approach comprises RL agents that partially observe the state of each machine to coordinate the decision-making in maintenance scheduling, resulting in the dynamic assignment of maintenance tasks to technicians (with different skills) over a set of machines. Experimental evaluation shows that our RL-based maintenance policy outperforms traditional maintenance policies (incl., corrective and preventive ones) in terms of failure prevention and downtime, improving by ≈75% the overall performance. [less ▲]

Full Text
Peer Reviewed
See detailAn Empirical Study on Data Distribution-Aware Test Selection for Deep Learning Enhancement
Hu, Qiang UL; Guo, Yuejun UL; Cordy, Maxime UL et al

in ACM Transactions on Software Engineering and Methodology (2022)

Similar to traditional software that is constantly under evolution, deep neural networks (DNNs) need to evolve upon the rapid growth of test data for continuous enhancement, e.g., adapting to distribution ... [more ▼]

Similar to traditional software that is constantly under evolution, deep neural networks (DNNs) need to evolve upon the rapid growth of test data for continuous enhancement, e.g., adapting to distribution shift in a new environment for deployment. However, it is labor-intensive to manually label all the collected test data. Test selection solves this problem by strategically choosing a small set to label. Via retraining with the selected set, DNNs will achieve competitive accuracy. Unfortunately, existing selection metrics involve three main limitations: 1) using different retraining processes; 2) ignoring data distribution shifts; 3) being insufficiently evaluated. To fill this gap, we first conduct a systemically empirical study to reveal the impact of the retraining process and data distribution on model enhancement. Then based on our findings, we propose a novel distribution-aware test (DAT) selection metric. Experimental results reveal that retraining using both the training and selected data outperforms using only the selected data. None of the selection metrics perform the best under various data distributions. By contrast, DAT effectively alleviates the impact of distribution shifts and outperforms the compared metrics by up to 5 times and 30.09% accuracy improvement for model enhancement on simulated and in-the-wild distribution shift scenarios, respectively. [less ▲]

Detailed reference viewed: 236 (61 UL)
Full Text
Peer Reviewed
See detailAdversarial Robustness in Multi-Task Learning: Promises and Illusions
Ghamizi, Salah UL; Cordy, Maxime UL; Papadakis, Mike UL et al

in Proceedings of the thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22) (2022)

Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks. While most of the studies focus on single-task neural networks with computer vision datasets, very little research ... [more ▼]

Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks. While most of the studies focus on single-task neural networks with computer vision datasets, very little research has considered complex multi-task models that are common in real applications. In this paper, we evaluate the design choices that impact the robustness of multi-task deep learning networks. We provide evidence that blindly adding auxiliary tasks, or weighing the tasks provides a false sense of robustness. Thereby, we tone down the claim made by previous research and study the different factors which may affect robustness. In particular, we show that the choice of the task to incorporate in the loss function are important factors that can be leveraged to yield more robust models. [less ▲]

Detailed reference viewed: 129 (8 UL)
Full Text
Peer Reviewed
See detailEfficient and Transferable Adversarial Examples from Bayesian Neural Networks
Gubri, Martin UL; Cordy, Maxime UL; Papadakis, Mike UL et al

in The 38th Conference on Uncertainty in Artificial Intelligence (2022)

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. We argue that transferability is ... [more ▼]

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. We argue that transferability is fundamentally related to uncertainty. Based on a state-of-the-art Bayesian Deep Learning technique, we propose a new method to efficiently build a surrogate by sampling approximately from the posterior distribution of neural network weights, which represents the belief about the value of each parameter. Our extensive experiments on ImageNet, CIFAR-10 and MNIST show that our approach improves the success rates of four state-of-the-art attacks significantly (up to 83.2 percentage points), in both intra-architecture and inter-architecture transferability. On ImageNet, our approach can reach 94% of success rate while reducing training computations from 11.6 to 2.4 exaflops, compared to an ensemble of independently trained DNNs. Our vanilla surrogate achieves 87.5% of the time higher transferability than three test-time techniques designed for this purpose. Our work demonstrates that the way to train a surrogate has been overlooked, although it is an important element of transfer-based attacks. We are, therefore, the first to review the effectiveness of several training methods in increasing transferability. We provide new directions to better understand the transferability phenomenon and offer a simple but strong baseline for future work. [less ▲]

Detailed reference viewed: 37 (5 UL)
Full Text
Peer Reviewed
See detailOn Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices
Ghamizi, Salah UL; Cordy, Maxime UL; Papadakis, Mike UL et al

in The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI- 23) - SafeAI Workshop, Washington, D.C., Feb 13-14, 2023 (2022)

Full Text
Peer Reviewed
See detailA Unified Framework for Adversarial Attack and Defense in Constrained Feature Space
Simonetto, Thibault Jean Angel UL; Dyrmishi, Salijona UL; Ghamizi, Salah UL et al

in Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22 (2022)

The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into ... [more ▼]

The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer vision. We propose a unified framework to generate feasible adversarial examples that satisfy given domain constraints. Our framework can handle both linear and non-linear constraints. We instantiate our framework into two algorithms: a gradient-based attack that introduces constraints in the loss function to maximize, and a multi-objective search algorithm that aims for misclassification, perturbation minimization, and constraint satisfaction. We show that our approach is effective in four different domains, with a success rate of up to 100%, where state-of-the-art attacks fail to generate a single feasible example. In addition to adversarial retraining, we propose to introduce engineered non-convex constraints to improve model adversarial robustness. We demonstrate that this new defense is as effective as adversarial retraining. Our framework forms the starting point for research on constrained adversarial attacks and provides relevant baselines and datasets that future research can exploit. [less ▲]

Detailed reference viewed: 13 (1 UL)
Full Text
Peer Reviewed
See detailLGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity
Gubri, Martin UL; Cordy, Maxime UL; Papadakis, Mike UL et al

in Computer Vision -- ECCV 2022 (2022)

We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects ... [more ▼]

We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects multiple weight sets from a few additional training epochs with a constant and high learning rate. LGV exploits two geometric properties that we relate to transferability. First, models that belong to a wider weight optimum are better surrogates. Second, we identify a subspace able to generate an effective surrogate ensemble among this wider optimum. Through extensive experiments, we show that LGV alone outperforms all (combinations of) four established test-time transformations by 1.8 to 59.9\% points. Our findings shed new light on the importance of the geometry of the weight space to explain the transferability of adversarial examples. [less ▲]

Detailed reference viewed: 24 (0 UL)
Full Text
Peer Reviewed
See detailEvasion Attack STeganography: Turning Vulnerability Of Machine Learning ToAdversarial Attacks Into A Real-world Application
Ghamizi, Salah UL; Cordy, Maxime UL; Papadakis, Mike UL et al

in Proceedings of International Conference on Computer Vision 2021 (2021)

Evasion Attacks have been commonly seen as a weakness of Deep Neural Networks. In this paper, we flip the paradigm and envision this vulnerability as a useful application. We propose EAST, a new ... [more ▼]

Evasion Attacks have been commonly seen as a weakness of Deep Neural Networks. In this paper, we flip the paradigm and envision this vulnerability as a useful application. We propose EAST, a new steganography and watermarking technique based on multi-label targeted evasion attacks. Our results confirm that our embedding is elusive; it not only passes unnoticed by humans, steganalysis methods, and machine-learning detectors. In addition, our embedding is resilient to soft and aggressive image tampering (87% recovery rate under jpeg compression). EAST outperforms existing deep-learning-based steganography approaches with images that are 70% denser and 73% more robust and supports multiple datasets and architectures. [less ▲]

Detailed reference viewed: 154 (25 UL)
Full Text
Peer Reviewed
See detailRequirements And Threat Models of Adversarial Attacks and Robustness of Chest X-ray classification
Ghamizi, Salah UL; Cordy, Maxime UL; Papadakis, Mike UL et al

E-print/Working paper (2021)

Vulnerability to adversarial attacks is a well-known weakness of Deep Neural Networks. While most of the studies focus on natural images with standardized benchmarks like ImageNet and CIFAR, little ... [more ▼]

Vulnerability to adversarial attacks is a well-known weakness of Deep Neural Networks. While most of the studies focus on natural images with standardized benchmarks like ImageNet and CIFAR, little research has considered real world applications, in particular in the medical domain. Our research shows that, contrary to previous claims, robustness of chest x-ray classification is much harder to evaluate and leads to very different assessments based on the dataset, the architecture and robustness metric. We argue that previous studies did not take into account the peculiarity of medical diagnosis, like the co-occurrence of diseases, the disagreement of labellers (domain experts), the threat model of the attacks and the risk implications for each successful attack. In this paper, we discuss the methodological foundations, review the pitfalls and best practices, and suggest new methodological considerations for evaluating the robustness of chest xray classification models. Our evaluation on 3 datasets, 7 models, and 18 diseases is the largest evaluation of robustness of chest x-ray classification models. We believe our findings will provide reliable guidelines for realistic evaluation and improvement of the robustness of machine learning models for medical diagnosis. [less ▲]

Detailed reference viewed: 132 (19 UL)
Full Text
Peer Reviewed
See detailA Replication Study on the Usability of Code Vocabulary in Predicting Flaky Tests
Haben, Guillaume UL; Habchi, Sarra UL; Papadakis, Mike UL et al

in 18th International Conference on Mining Software Repositories (2021, May)

Abstract—Industrial reports indicate that flaky tests are one of the primary concerns of software testing mainly due to the false signals they provide. To deal with this issue, researchers have developed ... [more ▼]

Abstract—Industrial reports indicate that flaky tests are one of the primary concerns of software testing mainly due to the false signals they provide. To deal with this issue, researchers have developed tools and techniques aiming at (automatically) identifying flaky tests with encouraging results. However, to reach industrial adoption and practice, these techniques need to be replicated and evaluated extensively on multiple datasets, occasions and settings. In view of this, we perform a replication study of a recently proposed method that predicts flaky tests based on their vocabulary. We thus replicate the original study on three different dimensions. First we replicate the approach on the same subjects as in the original study but using a different evaluation methodology, i.e., we adopt a time-sensitive selection of training and test sets to better reflect the envisioned use case. Second, we consolidate the findings of the initial study by building a new dataset of 837 flaky tests from 9 projects in a different programming language, i.e., Python while the original study was in Java, which comforts the generalisability of the results. Third, we propose an extension to the original approach by experimenting with different features extracted from the Code Under Test. Our results demonstrate that a more robust validation has a consistent negative impact on the reported results of the original study, but, fortunately, these do not invalidate the key conclusions of the study. We also find re-assuring results that the vocabulary-based models can also be used to predict test flakiness in Python and that the information lying in the Code Under Test has a limited impact in the performance of the vocabulary-based models [less ▲]

Detailed reference viewed: 230 (23 UL)
Full Text
Peer Reviewed
See detailA Formal Framework of Software Product Line Analyses
Castro, Thiago; Teixeira, Leopoldo; Alves, Vander et al

in ACM Transactions on Software Engineering and Methodology (2021), 30(3), 1-37

Detailed reference viewed: 83 (11 UL)
Full Text
Peer Reviewed
See detailBURST: a benchmarking platform for uniform random sampling techniques
Acher, Mathieu; Perrouin, Gilles; Cordy, Maxime UL

in SPLC '21: 25th ACM International Systems and Software Product Line Conference, Leicester, United Kindom, September 6-11, 2021, Volume B (2021)

Detailed reference viewed: 37 (0 UL)
Full Text
Peer Reviewed
See detailTest Selection for Deep Learning Systems
Ma, Wei UL; Papadakis, Mike UL; Tsakmalis, Anestis et al

in ACM Transactions on Software Engineering and Methodology (2021), 30(2), 131--1322

Detailed reference viewed: 387 (46 UL)
Full Text
Peer Reviewed
See detailTowards Exploring the Limitations of Active Learning: An Empirical Study
Hu, Qiang UL; Guo, Yuejun UL; Cordy, Maxime UL et al

in The 36th IEEE/ACM International Conference on Automated Software Engineering. (2021)

Deep neural networks (DNNs) are being increasingly deployed as integral parts of software systems. However, due to the complex interconnections among hidden layers and massive hyperparameters, DNNs ... [more ▼]

Deep neural networks (DNNs) are being increasingly deployed as integral parts of software systems. However, due to the complex interconnections among hidden layers and massive hyperparameters, DNNs require being trained using a large number of labeled inputs, which calls for extensive human effort for collecting and labeling data. Spontaneously, to alleviate this growing demand, a surge of state-of-the-art studies comes up with different metrics to select a small yet informative dataset for the model training. These research works have demonstrated that DNN models can achieve competitive performance using a carefully selected small set of data. However, the literature lacks proper investigation of the limitations of data selection metrics, which is crucial to apply them in practice. In this paper, we fill this gap and conduct an extensive empirical study to explore the limits of selection metrics. Our study involves 15 selection metrics evaluated over 5 datasets (2 image classification tasks and 3 text classification tasks), 10 DNN architectures, and 20 labeling budgets (ratio of training data being labeled). Our findings reveal that, while selection metrics are usually effective in producing accurate models, they may induce a loss of model robustness (against adversarial examples) and resilience to compression. Overall, we demonstrate the existence of a trade-off between labeling effort and different model qualities. This paves the way for future research in devising selection metrics considering multiple quality criteria. [less ▲]

Detailed reference viewed: 218 (48 UL)