Salah Ghamizi

According to our database, Salah Ghamizi authored at least 24 papers between 2015 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases.

Thibault Simonetto, Salah Ghamizi, Maxime Cordy

CoRR, 2024

SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Grids.

Salah Ghamizi, Aleksandar Bojchevski, Aoxiang Ma, Jun Cao

CoRR, 2024

Robustness Analysis of AI Models in Critical Energy Systems.

Pantelis Dogoulis, Matthieu Jimenez, Salah Ghamizi, Maxime Cordy, Yves Le Traon

CoRR, 2024

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data.

Thibault Simonetto, Salah Ghamizi, Maxime Cordy

CoRR, 2024

PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-Phase Distribution Systems.

Salah Ghamizi, Jun Cao, Aoxiang Ma, Pedro Rodriguez

CoRR, 2024

2023

Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data.

Thibault Simonetto, Salah Ghamizi, Antoine Desjardins, Maxime Cordy, Yves Le Traon

CoRR, 2023

Hazards in Deep Learning Testing: Prevalence, Impact and Recommendations.

Salah Ghamizi, Maxime Cordy, Yuejun Guo, Mike Papadakis, Yves Le Traon

CoRR, 2023

On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks.

Salijona Dyrmishi, Salah Ghamizi, Thibault Simonetto, Yves Le Traon, Maxime Cordy

Proceedings of the 44th IEEE Symposium on Security and Privacy, 2023

GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks.

Salah Ghamizi, Jingfeng Zhang, Maxime Cordy, Mike Papadakis, Masashi Sugiyama, Yves Le Traon

Proceedings of the International Conference on Machine Learning, 2023

How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks.

Salijona Dyrmishi, Salah Ghamizi, Maxime Cordy

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

On Evaluating Adversarial Robustness of Chest X-ray Classification.

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

Proceedings of the Workshop on Artificial Intelligence Safety 2023 (SafeAI 2023) co-located with the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), 2023

2022

Multi-objective Robust Machine Learning For Critical Systems With Scarce Data.

Salah Ghamizi

PhD thesis, 2022

On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices.

Salah Ghamizi, Maxime Cordy, Michail Papadakis, Yves Le Traon

CoRR, 2022

A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space.

Thibault Simonetto, Salijona Dyrmishi, Salah Ghamizi, Maxime Cordy, Yves Le Traon

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

Adversarial Robustness in Multi-Task Learning: Promises and Illusions.

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

A Hybrid Predictive Model for Mitigating Health and Economic Factors during a Pandemic.

Lisa Veiber, Salah Ghamizi, Jean-Sébastien Sottet

ERCIM News, 2021

Evasion Attack STeganography: Turning Vulnerability Of Machine Learning To Adversarial Attacks Into A Real-world Application.

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021

2020

Search-based adversarial testing and improvement of constrained credit scoring systems.

Salah Ghamizi, Maxime Cordy, Martin Gubri, Mike Papadakis, Andrey Boytsov, Yves Le Traon, Anne Goujon

Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Data-driven Simulation and Optimization for Covid-19 Exit Strategies.

Salah Ghamizi, Renaud Rwemalika, Maxime Cordy, Lisa Veiber, Tegawendé F. Bissyandé, Mike Papadakis, Jacques Klein, Yves Le Traon

Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

FeatureNET: diversity-driven generation of deep learning models.

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

Proceedings of the ICSE '20: 42nd International Conference on Software Engineering, Companion Volume, Seoul, South Korea, 27 June, 2020

2019

Adversarial Embedding: A robust and elusive Steganography and Watermarking technique.

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

CoRR, 2019

Automated Search for Configurations of Deep Neural Network Architectures.

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

CoRR, 2019

Automated search for configurations of convolutional neural network architectures.

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

Proceedings of the 23rd International Systems and Software Product Line Conference, 2019

2015

Re-typograph phase I: a proof-of-concept for typeface parameter extraction from historical documents.

Bart Lamiroy, Thomas Bouville, Julien Blégean, Hongliu Cao, Salah Ghamizi, Romain Houpin, Matthias Lloyd

Proceedings of the Document Recognition and Retrieval XXII, 2015