vix.ing · top · new · best · stats · spec

Watermarking and Anomaly Detection in Machine Learning Models for LORA RF Fingerprinting

2025/09/18 by Wayne Burleson, Mahajan, Aarushi, Burleson, Wayne
Computer Science · #Artificial Intelligence (cs.AI) #Chaos-based Image/Signal Encryption #Cryptography and Security (cs.CR) #Digital Media Forensic Detection #FOS: Computer and information sciences #FOS: Electrical engineering #Internet Traffic Analysis and Secure E-voting #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2509.15170

openalex publication_date 2025/09/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Radio frequency fingerprint identification (RFFI) distinguishes wireless devices by the small variations in their analog circuits, avoiding heavy cryptographic authentication. While deep learning on spectrograms improves accuracy, models remain vulnerable to copying, tampering, and evasion. We present a stronger RFFI system combining watermarking for ownership proof and anomaly detection for spotting suspicious inputs. Using a ResNet-34 on log-Mel spectrograms, we embed three watermarks: a simple trigger, an adversarially trained trigger robust to noise and filtering, and a hidden gradient/weight signature. A convolutional Variational Autoencoders (VAE) with Kullback-Leibler (KL) warm-up and free-bits flags off-distribution queries. On the LoRa dataset, our system achieves 94.6% accuracy, 98% watermark success, and 0.94 AUROC, offering verifiable, tamper-resistant authentication.

Citations

Related