Variational Secret Common Randomness Extraction

2025-10-02

AI Summary

This paper addresses the problem of extracting common randomness (CR) or secret keys from correlated random sources observed by Alice and Bob in the presence of an eavesdropper Eve. Conventional approaches suffer from reliance on channel reciprocity, high protocol overhead, and poor adaptability to mobile scenarios. To overcome these limitations, we propose a two-stage neural key generation framework based on variational probabilistic quantization: Stage I employs a probabilistic neural encoder with adversarial training to achieve highly consistent, low-leakage discrete mapping; Stage II integrates syndrome-based secure sketches to guarantee key secrecy. The method eliminates dependence on channel reciprocity and enables sensing-assisted physical-layer key generation. Simulation and software-defined radio experiments demonstrate that, even when Eve possesses partial location knowledge, the scheme achieves >98% key agreement rate and <0.05-bit information leakage—significantly enhancing practicality and security in high-mobility environments.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

This paper studies the problem of extracting common randomness (CR) or secret keys from correlated random sources observed by two legitimate parties, Alice and Bob, through public discussion in the presence of an eavesdropper, Eve. We propose a practical two-stage CR extraction framework. In the first stage, the variational probabilistic quantization (VPQ) step is introduced, where Alice and Bob employ probabilistic neural network (NN) encoders to map their observations into discrete, nearly uniform random variables (RVs) with high agreement probability while minimizing information leakage to Eve. This is realized through a variational learning objective combined with adversarial training. In the second stage, a secure sketch using code-offset construction reconciles the encoder outputs into identical secret keys, whose secrecy is guaranteed by the VPQ objective. As a representative application, we study physical layer key (PLK) generation. Beyond the traditional methods, which rely on the channel reciprocity principle and require two-way channel probing, thus suffering from large protocol overhead and being unsuitable in high mobility scenarios, we propose a sensing-based PLK generation method for integrated sensing and communications (ISAC) systems, where paired range-angle (RA) maps measured at Alice and Bob serve as correlated sources. The idea is verified through both end-to-end simulations and real-world software-defined radio (SDR) measurements, including scenarios where Eve has partial knowledge about Bob's position. The results demonstrate the feasibility and convincing performance of both the proposed CR extraction framework and sensing-based PLK generation method.

Problem

• Extracting secret keys from correlated sources with public discussion
• Minimizing information leakage to eavesdroppers during key generation
• Enabling secure key generation in high mobility communication scenarios

Innovation

• Variational probabilistic quantization with adversarial training
• Secure sketch code-offset construction for key reconciliation
• Sensing-based key generation using paired range-angle maps