RF Fingerprinting of DSP Implementations using Machine Learning: An Over-the-Air Case Study

arXiv:2610.15494 · eess.SP, cs.LG · Submitted 2026-10-11 · Read on arXiv

Listen

Transcript

Introduction to the show: ident: AI Radio. Generated commentary on the latest Artificial Intelligence papers.

Tom: I'm Tom.

Jane: And I'm Jane, here with Lu, Meng and our in-house large language model, Lalam.

Tom: Today's paper: "RF Fingerprinting of DSP Implementations using Machine Learning".

Jane: The gist: DSP-dependent fingerprinting can provide complementary information for specific emitter identification systems,

Tom: First, who's behind it and why it matters.

Paper summary: Tom: So we're looking at a paper called "RF Fingerprinting of DSP Implementations using Machine Learning: An Over-the-Air Case Study." Basically, it investigates if the way a digital signal processing algorithm is actually built leaves a detectable mark on the radio signal itself.

Jane: That sounds like it could be really interesting for identification systems. The main thing this paper claims is that you can tell different transmitters apart just by looking at how their digital processing handles the waveform, not by looking at the physical hardware imperfections in the transmitter.

Lu: It focuses on how algorithms for waveform generation leave classifiable DSP-dependent characteristics in the transmitted signal, which means it's moving away from just looking at analog stuff like filter shapes or oscillator noise.

Meng: But what does that actually mean for deploying something? If we can identify the specific software implementation rather than just a broad hardware class, how does that affect our ability to manage interference at scale?

Lalam: The paper applies a deep learning approach that trains neural networks exclusively on augmented software-generated data and evaluates it on over-the-air recordings obtained using a shortwave transceiver and a software-defined radio receiver.

Tom: Right, so they use convolutional neural networks trained on simulated signals that are distorted to mimic real world effects, and then they test those models against actual over-the-air recordings.

Jane: And the core finding is that for this specific case study involving five different software packages generating a two-FSK RTTY communication waveform, the best neural network combines raw IQ data and the power spectrum representation to achieve an accuracy of up to ninety percent <ref:2610.15494#pg1,generating a 2-FSK RTTY communication waveform>.

Lu: That's significant because it shows that these representations, using both raw IQ and the power spectrum, give you better results than just one or the other.

Meng: Ninety percent is good, but I need to know what those real-world conditions look like for deployment. The paper mentions examining the influence of SNR and receiver bandwidth on classification accuracy.

Tom: Exactly, because they found that it's advantageous to have high SNR or excess bandwidth for this type of fingerprinting. The best results came when both conditions were met simultaneously for the three-kHz passband setting <ref:2610.15494#pg3>.

Jane: So what this means for someone just listening to the show is that these identification systems work best when you have a pretty clear signal and enough signal width to see those DSP differences clearly in the power spectrum.

Lalam: The paper also looks at four different signal representations: raw IQ data, power spectrum using a one thousand twenty-four-point FFT, instantaneous frequency, and a combination of raw IQ data and its power spectrum.

Lu: They are testing how well each representation works when fed into the CNNs trained on that augmented software-generated data. It's about seeing which digital signal feature best captures the DSP differences they're looking for.

Tom: We see that the combination of raw IQ data and its power spectrum provides the best overall accuracy for classifying those different RTTY software implementations, which is a nice piece of practical advice for system design.

Jane: So, to wrap up this summary of "RF Fingerprinting of DSP Implementations using Machine Learning: An Over-the-Air Case Study," the authors are showing that DSP implementation details leave measurable characteristics in the radiated signal, and deep learning models can exploit those differences effectively.

Lu: The implication is that we can use these digital signal processing fingerprints as a complementary source of information for specific emitter identification systems, moving beyond just hardware imperfections.

Meng: From an engineering standpoint, it's interesting that they focused on the software side—the modulation shaping and quantization—rather than just assuming some analog component will always be different.

Tom: Yeah, and the authors are explicitly stating that they are investigating whether algorithms for waveform generation leave classifiable DSP-dependent characteristics in the transmitted signal, which sets a clear scope for what they achieved.

Jane: And looking at the title and authors, this paper is about using machine learning to fingerprint how software builds radio signals over the air. It seems like a practical look at making identification systems smarter by understanding the digital heart of the transmitter.

Conclusion: Tom: So we've been diving into how digital signal processing differences leave fingerprints on radio signals, and now we’re at the conclusion of this paper, "RF Fingerprinting of DSP Implementations using Machine Learning: An Over-the-Air Case Study."

Jane: Right. We looked at how different software packages for RTTY communication create slightly different signals because of how they process them digitally. This paper shows that these tiny digital differences can be used to identify the specific software being used, even when the signal looks almost identical in a time domain measurement like IQ data.

Lu: The core idea here is using machine learning, specifically convolutional neural networks, to classify those signals based on representations of raw IQ data and power spectra. They trained these models on simulated signals that had real-world distortions added to them.

Meng: So they’re saying you can use the way an algorithm is coded—the modulation shaping and the digital filtering—as a unique identifier for that transmitter, rather than just looking at some big hardware component like a digital-to-analog converter.

Lalam: Exactly. The paper found that using both raw IQ data and its power spectrum representation together gave them the best accuracy, reaching up to ninety percent on those over-the-air tests for the three kHz passband setting.

Tom: Ninety percent is solid when you look at real world signals, but they also pointed out some important conditions. They said that for this fingerprinting method to work well, you need either a high signal-to-noise ratio or an excess bandwidth in the signal.

Jane: That means if your radio receiver has a really clean signal and enough frequency space to see the spectrum clearly, your chances of getting an accurate identification go way up.

Lu: The paper suggests that this DSP-based fingerprinting can be a really useful tool for specific emitter identification systems because it provides information about the exact software implementation.

Meng: It moves us away from just classifying transmitters by their analog parts, which is what we usually do, toward identifying the specific digital brains behind the signal. That’s a different kind of classification problem altogether.

Tom: It definitely opens up a new avenue for SEI systems, showing that focusing on how the digital processing is implemented gives you a valuable layer of complementary information.

Jane: It does, and this investigation into DSP implementations provides a concrete component that we can use when building those specific emitter identification systems in the future.

Lu: So what we're seeing is that if you want to identify an emitter down to the software package level, this machine learning approach using these signal representations is a viable path forward.

Stefan Scholl

panoradio-sdr.de

eess.SP, cs.LG

Submitted: 2026-10-11

Updated: 2026-10-11

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: The gist: DSP-dependent fingerprinting can provide complementary information for specific emitter identification systems, as differences between digital signal processing implementations leave

Key concepts

Specific Emitter Identification (SEI): This is a radio monitoring task focused on recognizing specific transmitters rather than the general signal type. It seeks to exploit unique device characteristics embedded in the transmitted signal, which can be caused by variations in hardware or software implementations.
DSP-based RF Fingerprinting: This approach uses machine learning models trained on raw signal data (like IQ or power spectra) to differentiate transmitters based on how their underlying digital signal processing algorithms shape the output waveform. The goal is to identify differences arising from implementation details like modulation shaping or filtering.
RF Fingerprinting Features: The paper tested several features for fingerprinting, including raw IQ data, power spectrum (using FFT), and instantaneous frequency. These features are extracted from received signals to highlight subtle differences between transmitters that might be hidden in the time domain.
Machine Learning Classification: Convolutional Neural Networks (CNNs) were used as classifiers to analyze the extracted signal representations. These models automatically learn complex patterns from training data, allowing them to accurately classify a received signal into one of the known transmitter classes without requiring manual feature design.

Terminology

Fingerprinting — 1× in this paper · explained in 2 episodes

Summary

The gist: DSP-dependent fingerprinting can provide complementary information for specific emitter identification systems, as differences between digital signal processing implementations leave distinguishable characteristics in the transmitted signals

RF Fingerprinting for Specific Emitter Identification

Specific Emitter Identification (SEI) is a task in radio signal monitoring that focuses on the recognition of transmitters rather than the transmitted modulation or signal type or mode It seeks to exploit device-specific characteristics that are linked to the specific transmitters, which can be implemented through RF fingerprinting. These variations can generally originate from parts of the transmitter, such as analog electronics, digital-to-analog converter (DAC) properties, and digital signal processing (DSP) algorithms. Typical resulting signal characteristics that can be used for RF fingerprinting include details of the spectral shape from filters, spurious emissions from oscillators and non-linear blocks, signal transients, frequency and clock drifts, and phase noise properties.

Common Approaches to RF Fingerprinting

Classical RF fingerprinting typically follows a two-step approach: first, characteristic features are extracted from the received signal to emphasize signal differences between transmitters. Second, a classifier is applied to these features to determine the transmitter class. More recent approaches rely on deep learning algorithms, such as convolutional neural networks (CNNs), LSTMs and transformers, which can operate on raw signal representations like IQ or spectral data. These methods do not require the manual design of features but automatically learn the characteristic signal properties from a large amount of training data during a training process.

DSP-based RF Fingerprinting Approach

A typical transmitter consists of a combination of DSP, DAC and analog hardware. The waveform-generating DSP algorithms create the modulated signal in the digital domain and are implemented in software or as a digital circuit. The exact shape of the output signal depends on the details of the DSP implementation, including modulation shaping, digital filtering, and numerical quantization and rounding. The approach in this work aims to differentiate transmitters based on their DSP implementation rather than hardware implementations.

Case Study: AMATEUR RADIO COMMUNICATION

The study considers a 2-FSK RTTY communication waveform as a practical case study. Five different waveform-generation software packages for RTTY are considered, each representing one of the classes in the RF fingerprinting task. These software packages use different DSP implementations to generate the signal, leading to small differences that are not well visible in the time domain (IQ) but become more apparent in the power spectrum or instantaneous frequency representation. The study investigates four different signal representations for RF fingerprinting: raw IQ data, power spectrum using a 1024-point FFT, instantaneous frequency, and a combination of raw IQ data and its power spectrum.

Machine Learning Approach and Results

The paper uses CNNs to classify signals based on the signal representations, with different models used for each representation. The training data is generated using software simulation, where clean signals are augmented by various RF-related distortions to model real-world effects. Over-the-air tests are conducted using a shortwave transceiver and a software defined radio receiver. The results show that for SEI it is advantageous to have high SNR or excess bandwidth, with the best results achieved when both conditions are fulfilled. For the 3-kHz passband setting, the multi-input model using IQ and power spectrum provides the best overall accuracy. The results show that RF fingerprinting works particularly well for high SNR and if a wide signal bandwidth can be observed, achieving an accuracy of up to 90 % with over-the-air test signals.

Conclusion

DSP-related fingerprinting can provide an effective complementary source of information for SEI systems. The paper concludes that the investigation into DSP implementations provides a valuable component for specific emitter identification systems.

--- Page 7 ---