# RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation System

arXiv: https://arxiv.org/abs/2508.09186 · HTML: https://mlsanity.com/paper/2508.09186/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Privacy Preserving Image-Based Localization](https://mlsanity.com/paper/1903.05572/) (2019)
- [Reinforcement Learning with Token-level Feedback for Controllable Text Generation](https://mlsanity.com/paper/2403.11558/) (2024)
- [Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries](https://mlsanity.com/paper/2506.07555/) (2025)
- [Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions](https://mlsanity.com/paper/2209.04022/) (2022)
- [Improving Reinforcement Learning Based Image Captioning with Natural Language Prior](https://mlsanity.com/paper/1809.06227/) (2018)
- [FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation](https://mlsanity.com/paper/2410.22651/) (2024)
- [Privacy-Preserving in Connected and Autonomous Vehicles Through Vision to Text Transformation](https://mlsanity.com/paper/2506.15854/) (2025)

## Abstract (arXiv)

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.