Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.12537 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912330265133056 |
|---|---|
| author | Chehbouni, Khaoula De Cock, Martine Caporossi, Gilles Taik, Afaf Rabbany, Reihaneh Farnadi, Golnoosh |
| author_facet | Chehbouni, Khaoula De Cock, Martine Caporossi, Gilles Taik, Afaf Rabbany, Reihaneh Farnadi, Golnoosh |
| contents | The increased screen time and isolation caused by the COVID-19 pandemic have led to a significant surge in cases of online grooming, which is the use of strategies by predators to lure children into sexual exploitation. Previous efforts to detect grooming in industry and academia have involved accessing and monitoring private conversations through centrally-trained models or sending private conversations to a global server. In this work, we implement a privacy-preserving pipeline for the early detection of sexual predators. We leverage federated learning and differential privacy in order to create safer online spaces for children while respecting their privacy. We investigate various privacy-preserving implementations and discuss their benefits and shortcomings. Our extensive evaluation using real-world data proves that privacy and utility can coexist with only a slight reduction in utility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12537 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Privacy in the Early Detection of Sexual Predators Through Federated Learning and Differential Privacy Chehbouni, Khaoula De Cock, Martine Caporossi, Gilles Taik, Afaf Rabbany, Reihaneh Farnadi, Golnoosh Computation and Language Computers and Society The increased screen time and isolation caused by the COVID-19 pandemic have led to a significant surge in cases of online grooming, which is the use of strategies by predators to lure children into sexual exploitation. Previous efforts to detect grooming in industry and academia have involved accessing and monitoring private conversations through centrally-trained models or sending private conversations to a global server. In this work, we implement a privacy-preserving pipeline for the early detection of sexual predators. We leverage federated learning and differential privacy in order to create safer online spaces for children while respecting their privacy. We investigate various privacy-preserving implementations and discuss their benefits and shortcomings. Our extensive evaluation using real-world data proves that privacy and utility can coexist with only a slight reduction in utility. |
| title | Enhancing Privacy in the Early Detection of Sexual Predators Through Federated Learning and Differential Privacy |
| topic | Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2501.12537 |