kk

kassem kallas

I am a seasoned Research Scientist and Junior Professor specializing in Artificial Intelligence (AI) and Cyber security. I hold a Ph.D. in Information Engineering and Sciences from the University of Siena, Italy, where I focused on developing a Game-Theoretic approach for adversarial information fusion in distributed sensor networks within the cybersecurity domain. In June 2025, I obtained the Habilitation à Diriger des Recherches (HDR) degree from the University of Western Brittany (UBO), the highest academic qualification in the French university system. With extensive experience in both academia and industry, I have worked on projects funded by notable institutions such as DARPA, the U.S. Air Force Research Laboratory, the Italian Ministry of University and Research, and the French ANR and AID. My contributions include research on adversarial deep learning and signal processing, as well as AI security. I was a research fellow at the USA National Institute of Standards and Technology from February 2020 until the end of February 2022 in the wireless communication division of the chemical process and nuclear measurements group. From March 2022 to December 2023, I served as a research scientist at the French National Institute for Research in Digital Science and Technology (INRIA). Notable for my contributions to the SAIDA project, I focused on the security of AI for defense applications, exploring areas like backdoor attacks, deep learning defenses, and deep neural networks watermarking. I am currently a Senior Scientist at the French National Institute of Health and Medical Research, focusing on the security and privacy of AI for healthcare. My achievements include being recognized with the top 3 in the best-of-the-best PhD thesis award by Springer, the Best Paper Award at the Ninth International Conference on Advances in Multimedia (MMEDIA) in 2017, and the top $3\%$ paper award at the ICASSP conference in June 2023. As an author and editor, I have contributed to significant publications in the field, showcasing expertise in Game-theoretic concepts, pattern recognition, image processing, and machine learning security threats and defenses. I am an active member of professional organizations such as a Senior Member of IEEE, IEEE Young Professionals, IEEE Signal Processing Society, IEEE Entrepreneurship Exchange Community, IEEE Computer Society Technical Community on Security and Privacy, EURASIP, and APSIPA. In addition to professional pursuits, I volunteer as a mentor at IEEE Collabortec and as a Youth Volunteer at the Lebanese Red Cross. I recently graduated with an impressive average of 94.8\% from the Executive Master of Business Administration (EMBA) program in Strategic Leadership at Valar Institute, a division of Quantic School of Business and Technology, where I led and supervised a team of five individuals in developing a comprehensive business consultancy plan and pitch for a Swedish company, resulting in the team receiving full marks with outstanding reviews.
50 %
Libre accès
22
Documents
Affiliation actuelle
  • Senior Scientist
Identifiants chercheurs
Contact

Compétences

Aritificial Intelligence Leadership Strategic Planning Research and Development cyber security

Publications

Publications

Efficient Deep Learning-Based Decision Fusion for Adversarial Sensor Networks with Byzantine Attacks

Kassem Kallas

IEEE Sensors Journal, 2025, pp.1-1. ⟨10.1109/JSEN.2025.3566168⟩

Article dans une revue hal-05111045v1
Deposit thumbnail

RoSe-Mix: Robust and Secure Deep Neural Network Watermarking in Black-Box Settings via Image Mixup

Tamara El Hajjar , Mohammed Lansari , Reda Bellafqira , Gouenou Coatrieux , Katarzyna Kapusta et al.

Machine Learning and Knowledge Extraction, 2025, 7, ⟨10.3390/make7020032⟩

Article dans une revue hal-05110896v1

A Comprehensive Survey on Backdoor Attacks and Their Defenses in Face Recognition Systems

Quentin Le Roux , Eric Bourbao , Yannick Teglia , Kassem Kallas

IEEE Access, 2024, 12, pp.47433-47468. ⟨10.1109/ACCESS.2024.3382584⟩

Article dans une revue hal-04850549v1
Deposit thumbnail

Strategic safeguarding: A game theoretic approach for analyzing attacker-defender behavior in DNN backdoors

Kassem Kallas , Quentin Le Roux , Wassim Hamidouche , Teddy Furon

EURASIP Journal on Information Security, 2024, 2024 (1), pp.32. ⟨10.1186/s13635-024-00180-5⟩

Article dans une revue hal-05111061v1

A message passing approach for decision fusion in adversarial multi-sensor networks

Andrea Abrardo , Mauro Barni , Kassem Kallas , Benedetta Tondi

Information Fusion, 2018, 40, pp.101-111. ⟨10.1016/j.inffus.2017.06.006⟩

Article dans une revue istex hal-05111369v1

A Game-Theoretic Framework for Optimum Decision Fusion in the Presence of Byzantines

Andrea Abrardo , Mauro Barni , Kassem Kallas , Benedetta Tondi

IEEE Transactions on Information Forensics and Security, 2016, 11 (6), pp.1333-1345. ⟨10.1109/TIFS.2016.2526963⟩

Article dans une revue hal-05111486v1

Energy Backdoor Attack to Deep Neural Networks

Hanene Brachemi Meftah , Wassim Hamidouche , Sid Ahmed Fezza , Olivier Déforges , Kassem Kallas

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2025, Hyderabad, India. pp.1-5, ⟨10.1109/ICASSP49660.2025.10888330⟩

Communication dans un congrès hal-05111049v1

ROSE: A RObust and SEcure DNN Watermarking

Kassem Kallas , Teddy Furon

2022 IEEE International Workshop on Information Forensics and Security (WIFS), Dec 2022, Shanghai, France. pp.1-6, ⟨10.1109/WIFS55849.2022.9975300⟩

Communication dans un congrès hal-05111315v1

Deep Learning for Path Loss Prediction in the 3.5 GHz CBRS Spectrum Band

Thao Nguyen , Raied Caromi , Kassem Kallas , Michael Souryal

2022 IEEE Wireless Communications and Networking Conference (WCNC), Apr 2022, Austin, France. pp.1665-1670, ⟨10.1109/WCNC51071.2022.9771737⟩

Communication dans un congrès hal-05111332v1

Deep Learning for Radar Signal Detection in the 3.5 GHz CBRS Band

Raied Caromi , Alex Lackpour , Kassem Kallas , Thao Nguyen , Michael Souryal

2021 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Dec 2021, Los Angeles, France. pp.1-8, ⟨10.1109/DySPAN53946.2021.9677280⟩

Communication dans un congrès hal-05111342v1

CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis

Mauro Barni , Kassem Kallas , Ehsan Nowroozi , Benedetta Tondi

2020 IEEE International Workshop on Information Forensics and Security (WIFS), Dec 2020, New York, France. pp.1-6, ⟨10.1109/WIFS49906.2020.9360905⟩

Communication dans un congrès hal-05111352v1

On the Transferability of Adversarial Examples against CNN-based Image Forensics

M. Barni , Kassem Kallas , E. Nowroozi , B. Tondi

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, France. pp.8286-8290, ⟨10.1109/ICASSP.2019.8683772⟩

Communication dans un congrès hal-05111362v1

A New Backdoor Attack in CNNS by Training Set Corruption Without Label Poisoning

M. Barni , Kassem Kallas , B. Tondi

2019 IEEE International Conference on Image Processing (ICIP), Sep 2019, Taipei, France. pp.101-105, ⟨10.1109/ICIP.2019.8802997⟩

Communication dans un congrès hal-05111358v1

Luminance-based video backdoor attack against anti-spoofing rebroadcast detection

Abhir Bhalerao , Kassem Kallas , Benedetta Tondi , Mauro Barni

2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP), Sep 2019, Kuala Lumpur, France. pp.1-6, ⟨10.1109/MMSP.2019.8901711⟩

Communication dans un congrès hal-05111356v1

Decision Fusion with Unbalanced Priors under Synchronized Byzantine Attacks: a Message-Passing Approach

Andrea Abrardo , Mauro Barni , Kassem Kallas , Benedetta Tondi

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Nov 2018, Honolulu, France. pp.1160-1167, ⟨10.23919/APSIPA.2018.8659667⟩

Communication dans un congrès hal-05111365v1
Deposit thumbnail

A Message Passing Approach for Decision Fusion of Hidden-Markov Observations in the Presence of Synchronized Attacks

Kassem Kallas , Mauro Barni , Andrea Abrardo , Benedetta Tondi

The Ninth International Conferences on. Advances in Multimedia. MMEDIA 2017, Apr 2017, Venice, Italy

Communication dans un congrès hal-05111380v1
Deposit thumbnail

Consensus Algorithm with Censored Data for Distributed Detection with Corrupted Measurements: A Game-Theoretic Approach

Kassem Kallas , Benedetta Tondi , Riccardo Lazzeretti , Mauro Barni

7th International Conference on Decision and Game Theory for Security, Springer, Nov 2016, New York, United States. pp.455-466, ⟨10.1007/978-3-319-47413-7_26⟩

Communication dans un congrès hal-05111504v1

Decision fusion with corrupted reports in multi-sensor networks: A game-theoretic approach

A. Abrardo , M. Barni , Kassem Kallas , B. Tondi

2014 IEEE 53rd Annual Conference on Decision and Control (CDC), Dec 2014, Los Angeles, United States. pp.505-510, ⟨10.1109/CDC.2014.7039431⟩

Communication dans un congrès hal-05111513v1