Raouf Kerkouche


Postdoctoral Researcher
CISPA Helmholtz Center for Information Security
raouf.kerkouche at cispa.de

Google Scholar| LinkedIn| Twitter

About me| Publications| Awards| Mentoring| Service| Teaching

About me


I am a postdoctoral researcher at CISPA Helmholtz Center for Information Security (Germany) and I am working with Prof. Mario Fritz on Trustworthy Machine Learning with a focus on Security & Privacy. I am also affiliated with the Chair on legal and regulatory implications of artificial intelligence. Before joining CISPA, I was a Ph.D. student in computer science at Inria Grenoble in the Privatics team under the supervision of Prof. Claude Castelluccia (Privatics team-Inria) and Prof. Pierre Genevès (LIG and Tyrex team-Inria). Prior to that, I had the privilege of working with Prof. Mérouane Debbah.

I am on the job market! Please check out my CV for more details.

News


[2024/10] I am honored to serve as a Program Committee member for the renowned CCS 2025 Conference 📢

[2024/09] We are pleased to announce the organization of a new competition on Inference Attacks Against Document Visual Question Answering (DocVQA) Models, to be held at SaTML 2025. For more details, please visit the competition page here.

Publications


Privacy-Aware Document Visual Question Answering
Rubèn Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, Joonas Jälkö, Vincent Poulain D’Andecy, Aurelie Joseph, Lei Kang, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas.
Proceedings of the 18th International Conference on Document Analysis and Recognition (ICDAR 2024)
pdf code

A Unified View of Differentially Private Deep Generative Modeling
Dingfan Chen, Raouf Kerkouche, Mario Fritz.
Proceedings of Transactions on Machine Learning Research (TMLR 2024). [Survey Certification]
pdf

Private and Collaborative Kaplan-Meier Estimators
Shadi Rahimian, Raouf Kerkouche, Mario Fritz.
Proceedings of the 23nd Workshop on Privacy in the Electronic Society (WPES 2024), held in conjunction with CCS 2024
pdf

FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations
Hui-Po Wang, Dingfan Chen, Raouf Kerkouche, Mario Fritz.
Proceedings of the 24th Privacy Enhancing Technologies Symposium (PETS 2024)
pdf code

Towards Biologically Plausible and Private Gene Expression Data Generation
Dingfan Chen, Marie Oestreich, Tejumade Afonja, Raouf Kerkouche, Matthias Becker, Mario Fritz.
Proceedings of the 24th Privacy Enhancing Technologies Symposium (PETS 2024)
pdf code

Client-specific Property Inference against Secure Aggregation in Federated Learning
Raouf Kerkouche, Gergely Ács, Mario Fritz.
Proceedings of the 22nd Workshop on Privacy in the Electronic Society (WPES 2023), held in conjunction with CCS 2023
pdf code

Private Set Generation with Discriminative Information
Dingfan Chen, Raouf Kerkouche, Mario Fritz.
Proceedings of the Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022)
pdf code

Practical Challenges in Differentially-Private Federated Survival Analysis of Medical Data
Shadi Rahimian, Raouf Kerkouche, Ina Kurth, Mario Fritz.
Proceedings of the Conference on Health, Inference, and Learning (ACM CHIL 2022)
pdf

Constrained Differentially Private Federated Learning for Low-bandwidth Devices
Raouf Kerkouche, Gergely Ács, Claude Castelluccia, Pierre Genevès
Proceedings of the thirty-seventh conference on Uncertainty in Artificial Intelligence (UAI 2021)
pdf

Compression Boosts Differentially Private Federated Learning
Raouf Kerkouche, Gergely Ács, Claude Castelluccia, Pierre Genevès
Proceedings of the 6th IEEE European Symposium on Security and Privacy (IEEE EuroS&P 2021)
pdf

Privacy-Preserving and Bandwidth-Efficient Federated Learning: An Application to In-Hospital Mortality Prediction
Raouf Kerkouche, Gergely Ács, Claude Castelluccia, Pierre Genevès
Proceedings of the Conference on Health, Inference, and Learning (ACM CHIL 2021)
pdf code

Federated Learning in Adversarial Settings
Raouf Kerkouche, Gergely Ács, Claude Castelluccia
arXiv 2020
pdf

Awards


[2023] SaTML 2023 - Notable reviewer award

Mentoring


Dingfan Chen @CISPA
Shadi Rahimian @CISPA
Tejumade Afonja @CISPA
Hui-Po Wang @CISPA
Laszlo Fetter @BME

Service


PC Member (Conferences): CCS 2025, AISTATS 2025, CCS 2024, AISTATS 2024, IEEE SaTML 2024, AISTATS 2023, IEEE SaTML 2023
PC Member (Workshops): CCS AISec 2023, NeurIPS AFT 2023, NeurIPS AFCP 2022, AAAI PPAI 2022
Journals Reviewer: Nature Medicine 2023, ACM TOPS 2022, ECML PKDD 2022 (journal track)
External Reviewer: ICLR 2025, IEEE EuroS&P 2021
Organized Competitions: Privacy Preserving Federated Learning Document VQA (NeurIPS 2023 Competition)

Teaching


@Teaching Assistant and Lecturer on Machine Learning in Cybersecurity
- Institution / Program: Saarland University and Leibniz University, Master degree.
- Duration / Language: 80 hours, English
- Content: Machine Learning (ML) for improving security, Attacks on ML, Defenses for ML, ML and Privacy, Security of Large Language Models.