Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.09186 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911106004418560 |
|---|---|
| author | Rezaei, Abdolazim Sookhak, Mehdi Haghparast, Mahboobeh |
| author_facet | Rezaei, Abdolazim Sookhak, Mehdi Haghparast, Mahboobeh |
| contents | The proliferation of AI-powered cameras in Intelligent Transportation Systems (ITS) creates a severe conflict between the need for rich visual data and the right to privacy. Existing privacy-preserving methods, such as blurring or encryption, are often insufficient due to creating an undesirable trade-off where either privacy is compromised against advanced reconstruction attacks or data utility is critically degraded. To resolve this challenge, we propose RL-MoE, a novel framework that transforms sensitive visual data into privacy-preserving textual descriptions, eliminating the need for direct image transmission. RL-MoE uniquely combines a Mixture-of-Experts (MoE) architecture for nuanced, multi-aspect scene decomposition with a Reinforcement Learning (RL) agent that optimizes the generated text for a dual objective of semantic accuracy and privacy preservation. Extensive experiments demonstrate that RL-MoE provides superior privacy protection, reducing the success rate of replay attacks to just 9.4\% on the CFP-FP dataset, while simultaneously generating richer textual content than baseline methods. Our work provides a practical and scalable solution for building trustworthy AI systems in privacy-sensitive domains, paving the way for more secure smart city and autonomous vehicle networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09186 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System Rezaei, Abdolazim Sookhak, Mehdi Haghparast, Mahboobeh Computer Vision and Pattern Recognition Artificial Intelligence The proliferation of AI-powered cameras in Intelligent Transportation Systems (ITS) creates a severe conflict between the need for rich visual data and the right to privacy. Existing privacy-preserving methods, such as blurring or encryption, are often insufficient due to creating an undesirable trade-off where either privacy is compromised against advanced reconstruction attacks or data utility is critically degraded. To resolve this challenge, we propose RL-MoE, a novel framework that transforms sensitive visual data into privacy-preserving textual descriptions, eliminating the need for direct image transmission. RL-MoE uniquely combines a Mixture-of-Experts (MoE) architecture for nuanced, multi-aspect scene decomposition with a Reinforcement Learning (RL) agent that optimizes the generated text for a dual objective of semantic accuracy and privacy preservation. Extensive experiments demonstrate that RL-MoE provides superior privacy protection, reducing the success rate of replay attacks to just 9.4\% on the CFP-FP dataset, while simultaneously generating richer textual content than baseline methods. Our work provides a practical and scalable solution for building trustworthy AI systems in privacy-sensitive domains, paving the way for more secure smart city and autonomous vehicle networks. |
| title | RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.09186 |