Please refer to Google Scholar for the latest updates.

Published

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
Chehbouni Khaoula, Roshan Megha, Ma Emmanuel, Andrew Wei Futian, Taik Afaf, Cheung Jackie CK, Farnadi Golnoosh
Findings of the Association for Computational Linguistics ACL 2024
[paper]

Early Detection of Sexual Predators with Federated Learning
Chehbouni Khaoula, Caporossi Gilles, Rabbany Reihaneh, De Cock Martine, Farnadi Golnoosh
Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022)
[paper]

AI and Cities: Risks, Applications and Governance
UN-Habitat and Mila
4th Urban Economy Forum Conference 2022 [paper]

Unmasking Predators: Safeguarding Vulnerable Moroccan Communities Post-Earthquake
Taïk, Afaf, Chehbouni, K., Jain*, Kanishk, Akinfaderin Wale, Bouzoubaa Karim, Farnadi Golnoosh, Tazi Nouamane
North Africans in Machine Learning at NeurIPS 2023

Leveraging AI for Natural Disaster Management: Takeaways From The Moroccan Earthquake
Lena Nehale Ezzine, Bengio Yoshua, Atanane Ayoub et al.
6th Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response at NeurIPS 2023

Forthcoming

Enhancing Privacy in Early Detection of Online Grooming Through Federated Learning and Differential Privacy
Chehbouni Khaoula, De Cock Martine, Caporossi Gilles, Rabbany Reihaneh, Farnadi Golnoosh

Systematic Hazard Taxonomy Along the AI Lifecycle
Chehbouni Khaoula, et al.

Auditing the Helpful and Harmless Dataset
Chehbouni* Khaoula and Colaço Carr* Jonathan, More Yash, Cheung CK Jackie, Farnadi Golnoosh