Abstract Layer for LeakyReLU for Neural Network Verification Based on Abstract Interpretation

Autor: Omar El Mellouki, Mohamed Ibn Khedher, Mounim A. El-Yacoubi

Publikováno v: IEEE Access, Vol 11, Pp 33401-33413 (2023)

Deep neural networks have been widely used in several complex tasks such as robotics, self-driving cars, medicine, etc. However, they have recently shown to be vulnerable in uncertain environments where inputs are noisy. As a consequence, the robustn

Externí odkaz: https://doaj.org/article/5d72c298a9df4d08b3c11d0e701472cb

Constrained Clustering Problems: NewOptimization Algorithms

Autor: Selma Khebbache, Mohamed Ibn Khedher, Hatem Ibn-Khedher, Makhlouf Hadji

Publikováno v: International conference on Artificial Intelligence and Soft Computing
International conference on Artificial Intelligence and Soft Computing, Jun 2021, Zakopane, Poland
Artificial Intelligence and Soft Computing ISBN: 9783030878962
ICAISC (2)

Constrained clustering problems are often considered in massive data clustering and analysis. They are used in modeling various issues in anomaly detection, classification, systems’ misbehaviour, etc. In this paper, we focus on generalizing the K-M

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2e57729c6dcee8c3618da615e486dd4
https://hal.archives-ouvertes.fr/hal-03400812

Dynamic and Scalable Deep Neural Network Verification Algorithm

Autor: Mohamed Ibn Khedher, Hatem Ibn-Khedher, Makhlouf Hadji

Publikováno v: International Conference on Agents and Artificial Intelligence
International Conference on Agents and Artificial Intelligence, Feb 2021, Vienna, Austria
ICAART (2)

International audience

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1c0d075d4ccef8a6a8cc10d4a9be5e3
https://hal.archives-ouvertes.fr/hal-03043107

Analyzing Adversarial Attacks against Deep Learning for Robot Navigation

Autor: Mehdi Rezzoug, Mohamed Ibn Khedher

Publikováno v: ICAART (2)
International Conference on Agents and Artificial Intelligence
International Conference on Agents and Artificial Intelligence, Feb 2021, Vienna, Austria

International audience

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3f10ae6bb48898868799d72dadcc53f
https://doi.org/10.5220/0010323611141121

Safety and Robustness of Deep Neural Networks Object Recognition Under Generic Attacks

Autor: Asma Trabelsi, Dimitri Bettebghor, Mallek Mziou Sallami, Mohamed Ibn Khedher, Samy Kerboua-Benlarbi

Publikováno v: 26th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Society
26th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Society, Dec 2019, Sydney, Australia. pp.274-286, ⟨10.1007/978-3-030-36808-1_30⟩
Communications in Computer and Information Science ISBN: 9783030368074
ICONIP (4)

Embedding machine or deep learning software into safety-critical systems such as autonomous vehicles requires software verification and validation. Such software adds non traceable hazards to traditional hardware and sensors failures, not to mention

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b8b91c830f4c3eb95b00dada49fe0db
https://hal.archives-ouvertes.fr/hal-02473613