Privacy-Concealing Cooperative Perception for BEV Scene Segmentation

2026-02-14

AI Summary

This work addresses the privacy risks inherent in collaborative perception systems for autonomous driving, where sharing visual data can lead to the leakage of sensitive information. To mitigate this, the authors propose the Privacy-Concealed Collaboration (PCC) framework, which introduces adversarial learning into collaborative perception for the first time. PCC embeds a hiding network at the bird’s-eye-view (BEV) feature level to prevent the receiver from reconstructing the original images. Through adversarial training, the framework jointly optimizes BEV feature encoding, image reconstruction, and the hiding network, enabling end-to-end collaboration between privacy preservation and semantic segmentation. Experimental results demonstrate that PCC substantially reduces image reconstructability—thereby enhancing privacy—while imposing minimal degradation on BEV semantic segmentation performance.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Privacy
• Multiagent Systems: Adversarial Agents

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Cooperative perception systems for autonomous driving aim to overcome the limited perception range of a single vehicle by communicating with adjacent agents to share sensing information. While this improves perception performance, these systems also face a significant privacy-leakage issue, as sensitive visual content can potentially be reconstructed from the shared data. In this paper, we propose a novel Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation. Based on commonly shared BEV features, we design a hiding network to prevent an image reconstruction network from recovering the input images from the shared features. An adversarial learning mechanism is employed to train the network, where the hiding network works to conceal the visual clues in the BEV features while the reconstruction network attempts to uncover these clues. To maintain segmentation performance, the perception network is integrated with the hiding network and optimized end-to-end. The experimental results demonstrate that the proposed PCC framework effectively degrades the quality of the reconstructed images with minimal impact on segmentation performance, providing privacy protection for cooperating vehicles. The source code will be made publicly available upon publication.

Problem

• privacy leakage
• cooperative perception
• BEV segmentation
• visual reconstruction
• autonomous driving

Innovation

• Privacy-Concealing Cooperation
• BEV segmentation
• adversarial learning
• feature hiding
• cooperative perception