FRW-TRACE: Forensic-Ready Watermarking Framework for Tamper-Resistant Biometric Data and Attack Traceability in Consumer Electronics

With the widespread adoption of biometric technology in consumer electronics (e.g., smart locks, wearables), biometric data transmission increasingly faces security threats like relay attacks, tampering, and spoofing. Traditional passive defenses are ineffective in anonymized traffic tracing, suffer from high latency, and lack adaptability. Network flow watermarking (NFW), an active traffic analysis technique, embeds covert identifiers to secure biometric data and trace attacks. However, existing solutions in consumer electronics still face challenges, including synchronization instability, detectability risks, and the trade-off between robustness and concealment. To address these challenges, we propose FRW-TRACE, a forensic-ready watermarking framework with enhanced traceability, which innovatively integrates temporal group statistical features and packet sequence features as a dual-modal embedding carrier. To mitigate synchronization loss due to temporal perturbations, we develop a packet sequence-based synchronization mechanism that ensures reliable extraction of synchronization information. Additionally, to alleviate watermark degradation in high packet loss environments, we design an interval packet counting-based resilient encoding strategy, which improves watermark robustness against network disruptions and effectively evades detection by the Kolmogorov-Smirnov (K-S) test. Extensive experimental evaluations demonstrate that FRW-TRACE achieves an average detection accuracy of 100% under high latency jitter conditions and maintains over 90% accuracy in high packet loss scenarios. Furthermore, comparative analysis shows that under identical interference conditions, FRW-TRACE improves detection accuracy by 2%-4% compared to the state-of-the-art NFW methods.