CILC: Cryptographically-secure Inter-agent Loop Closure Candidate Detection for Multi-Agent Collaborative SLAM

2026-07-07

AI Summary

This work addresses the privacy vulnerability in multi-agent collaborative SLAM, where exchanging global descriptors for inter-agent loop closure detection risks exposing trajectories and environmental information to compromised agents. To mitigate this, the study introduces secure multi-party computation (SMPC) into the loop closure pipeline—marking the first such application in this domain—enabling encrypted similarity comparisons without transmitting plaintext descriptors. The proposed method supports both visual and LiDAR modalities and achieves privacy-preserving loop candidate detection while maintaining real-time performance and communication efficiency. Experimental validation in both simulation and hardware platforms demonstrates that the approach effectively prevents information leakage without sacrificing system responsiveness or accuracy.

Abstract

Multi-agent Simultaneous Localization and Mapping (SLAM) and collaborative SLAM (CSLAM) require robots to continuously exchange global descriptors (GDs) to detect inter-agent loop closures (ILCs). While encrypted radios protect this traffic from external eavesdroppers, they offer no protection against a compromised swarm member. We show this threat is concrete by demonstrating how a corrupted agent can reconstruct approximations of an honest agent's imagery and trajectory from its public GD broadcasts. To address this, we propose CILC (Cryptographically-secure Inter-agent Loop Closure candidate detection), a first-of-its-kind system leveraging Secure Multi-Party Computation (SMPC) to detect ILC candidates without exchanging GDs in the clear. Rather than securing the entire CSLAM pipeline, we apply SMPC only to ILC candidate detection (i.e., GD similarity comparison), a privacy-sensitive yet computationally lightweight step, yielding an advantageous privacy-to-overhead trade-off. We validate in both simulation and hardware experiments that CILC remains real-time and communication-feasible across multimodal GDs (visual and LiDAR), while mitigating information leakage to a compromised swarm agent.

Problem

• Multi-Agent SLAM
• Inter-agent Loop Closure
• Privacy Leakage
• Global Descriptors
• Compromised Agent

Innovation

• Secure Multi-Party Computation
• Inter-agent Loop Closure
• Collaborative SLAM
• Privacy-preserving Robotics
• Global Descriptors