Machine learning (ML) decoders are increasingly used in quantum error correction (QEC) to model noise, analyze imperfect syndrome measurements, and replace iterative matching algorithms with a learned inference pass, making them a critical component of the classical control stack of a fault-tolerant quantum computer. Prior security analysis of the ML decoders in the controller stack has addressed integrity and fault-injection attacks on the decoders. This work is the first to explore physical power side-channel attacks on ML decoders. In particular, it studies a convolutional Deep Q-Learning decoder for the distance-5 surface code. This work profiles the decoder to capture the power signatures generated during classification tasks and trains a classifier to identify which qubit the decoder identified as having errors based on the power signatures. The trained classifier is then applied to test data, where it recovers the correct data qubit label from the decoder’s side-channel data with up to \(83.2\%\) accuracy across 25 classes, against \(4\%\) for random guessing. A second classifier is trained to identify the type of error labeled by the decoder, Pauli X or Z, and reaches \(84.6\%\) accuracy, against \(50\%\) for random guessing. This work further performs an initial study of a timing channel, which complements the power side channels, exploring how the duration of the decoder’s first convolutional layer can leak the code size for which the decoder is compiled. All the side-channel attacks demonstrated in this work motivate treating the embedded QEC decoder as a confidentiality-critical component of the quantum control stack.
Machine learning (ML) decoders are increasingly used in quantum error correction (QEC) to model noise, analyze imperfect syndrome measurements, and replace iterative matching algorithms with a learned inference pass, making them a critical component of the classical control stack of a fault-tolerant quantum computer. Prior security analysis of the ML decoders in the controller stack has addressed integrity and fault-injection attacks on the decoders. This work is the first to explore physical power side-channel attacks on ML decoders. In particular, it studies a convolutional Deep Q-Learning decoder for the distance-5 surface code. This work profiles the decoder to capture the power signatures generated during classification tasks and trains a classifier to identify which qubit the decoder identified as having errors based on the power signatures. The trained classifier is then applied to test data, where it recovers the correct data qubit label from the decoder’s side-channel data with up to (83.2%) accuracy across 25 classes, against (4%) for random guessing. A second classifier is trained to identify the type of error labeled by the decoder, Pauli X or Z, and reaches (84.6%) accuracy, against (50%) for random guessing. This work further performs an initial study of a timing channel, which complements the power side channels, exploring how the duration of the decoder’s first convolutional layer can leak the code size for which the decoder is compiled. All the side-channel attacks demonstrated in this work motivate treating the embedded QEC decoder as a confidentiality-critical component of the quantum control stack.
Machine-learning (ML) models are increasingly used in quantum computing systems to discriminate multi-qubit readouts, mitigate correlated readout errors, and decode quantum error-correcting codes, making them an integral component of today's quantum computer control and readout stacks. This paper is the first to analyze the susceptibility of such ML models to physical fault injection, which can cause quantum computers to return incorrect results or perform wrong error correction operation. This work studies two representative architectures: (i) a fully connected neural network for 5-qubit (32-class) readout error correction (HERQULES), and (ii) a convolutional neural network used as a Deep Q-learning (Deep Q) decoder for the distance-5 Surface Code. Using the ChipWhisperer Husky for voltage glitching together with automated search over the fault parameter space, this work localizes successful fault settings to specific layers of each target ML model. On the HERQULES model, fault susceptibility is strongly layer-dependent: early layers exhibit higher misprediction rates than later layers. On the Deep Q decoder, a single trigger-aligned voltage glitch in either the first convolutional layer or the final fully connected output layer reduces decoding accuracy from 100% to as low as 21.57%. We further characterize the resulting failures at the bitstring level using Hamming-distance and per-bit flip statistics, showing that single-shot glitches can induce structured corruption rather than purely random noise. These results motivate treating ML-based quantum readout and error-correction decoding as security-critical components, and highlight the need for lightweight fault-detection and redundancy mechanisms in quantum computing pipelines.
As quantum computing emerges as an applied technology, there is a growing need to protect quantum computers against information security attacks. This work identifies a new class of side-channel attacks against fault-tolerant quantum computers, in which the syndrome data that is sent to the decoder system is used to infer which computation (logical circuit) is taking place on the quantum computer. Our work introduces the concept of gate fingerprints, which describes those patterns present in syndrome data that indicate which logical operation took place on the quantum computer. We show different effects by which logical operations produce gate fingerprints by focusing on Clifford+T computation in the surface code. We then explore how gate fingerprint information can be used to make inferences about the circuits or algorithms run on a quantum computer. Our findings indicate that decoder systems can be a vector for side-channel attacks and thus to prevent this, decoder systems should either be secured or built by a trusted party.
Quantum computation has the promise to solve problems that are not efficiently solvable by classical means. Yet, due to the fragile nature of quantum states, it is unavoidable that quantum systems are subject to decoherence, gate imperfections, and measurement errors. These problems stand as a major roadblock to the construction of large-scale fault-tolerant quantum computers. Conventional quantum error correction (QEC) codes, such as the surface code or Shor code, need to use an extensive amount of redundancy and classical control, which can be both computationally expensive and challenging to scale. In this context, we propose to investigate the use of machine learning (ML) techniques by realizing on-line identification, localization and correction of these quantum errors for fault-tolerant quantum computation by means of fault-tolerant quantum computing processes. Our model introduces a hybrids ML-QEC architecture that combines classical neural networks and decision-tree classifiers with quantum syndrome decoding. These models are trained on error syndromes produced using the approximation of common noise models (for example, depolarizing noise, dephasing and amplitude damping), simulated under different QEC schemes. The machine learning methods are trained with quantum error patterns and have a capability to rapidly infer where errors are likely to occur, as well as recommend correction operations with high confidence. As a result, the system reduces dramatically the delay and computational costs when compared to conventional decoding methods. There is also a self-adaptive learning module in the work, which recommences training on fresh quantum error distributions, meaning the system can adapt to changes in the environment (and also the decay of the hardware) as time progresses. The study further carries out ML predictions inside a real-time loop and cross-checks them with quantum state tomography and entanglement fidelity such as indicators. Experimental characterization on dedicated devices as well as noise models show that our ML-enhanced decoders reach higher fidelity and lower logical error rates compared to baseline decoders, especially in non-uniform or time-dependent noise. This work is a significant stride towards realizing practical fault-tolerant quantum computation by combining quantum error correction with the versatility and scalability of machine learning. With intelligent models to dictate learning, our proposed framework is able to eliminate a lot of trial-and-error manual processes in the conventional heuristic-based approach, and points to a potential path to achieve scalable quantum information processing platforms.
Neural network decoders are essential for fault-tolerant quantum computation, yet their internal mechanisms remain poorly understood. Leading machine learning decoders use recurrent and transformer models (e.g., AlphaQubit), and reinforcement learning (RL) is increasingly used to train such models. In this work we ask whether an RL surface code decoder, DeepQ, can be made to fail systematically. Our white-box search repeatedly draws candidate syndrome volumes from the unmodified noise model and retains the one the decoder's learned Q-function is most pessimistic about. At code distance 5 under phenomenological depolarising noise, it cuts the average logical qubit lifetime from roughly 105 cycles to 60. We quantify what this costs: the retained error histories are individually plausible, but the selected trajectory is roughly a 10−18 tail event under undisturbed noise, so the effect is bought entirely by the ability to select among physically realisable error configurations. Controls confirm this is not an artefact of a weak target: the decoder resists noise fluctuations, tolerates an MWPM referee, and is fault tolerant at checkable distances. The result is a robustness upper bound for one decoder under one noise model, but to our knowledge the first adversarial attack of a machine learning QEC decoder.
Quantum error correction (QEC) is the most promising route toward fault-tolerant quantum computing and, thus, useful quantum computers. QEC operates as a continuous measure-decode-correct cycle: ancilla qubits are read out, a decoder infers errors from the resulting syndromes, and corrections are applied before the next round begins. Within this loop, readout occupies a uniquely critical role, as it is the sole source of ground truth available to the decoder. Yet readout is also the slowest and most error-prone operation in the stack, with characteristics that vary across qubits and drift over time; This complexity propagates directly to the classical control hardware, and in particular to the FPGA-hosted machine-learning (ML) discriminator that must classify each analog signal into a binary syndrome outcome. Despite this central role, QEC performance has not yet been studied in depth from the perspective of readout characteristics, readout length, and their co-design with an ML discriminator.
We introduce Oraqle, an end-to-end benchmarking framework that evaluates qubit-state readout and its impact on QEC performance across real experimentally extracted qubit-state-readout datasets, state-of-the-art ML discriminators, multiple QEC codes, and hardware regimes spanning current to projected devices. Our study reveals three asymmetric findings: The measurement duration can be significantly reduced with nearly no penalty to the logical error rate; The discriminator complexity barely affects the QEC performance, as residual errors are written into device physics rather than the model; and the impact of qubit-state readout on the logical error rate is conditional on where the hardware sits in the QEC landscape, a window that widens as devices mature.
Decoding is an essential component of quantum error correction (QEC), translating stabilizer measurement outcomes into corrective actions that suppress logical errors and preserve logical quantum information. Building fault-tolerant architectures requires increasing the code distance, which in turn places growing demands on decoding accuracy, scalability, and practical deployability. While a wide range of decoding algorithms have been proposed and demonstrated, achieving reliable, scalable, and real-time decoding remains a significant challenge. Machine-learning (ML) approaches are particularly well suited to this setting, as quantum error decoding is fundamentally a problem of processing large volumes of classical data with complex spatiotemporal correlations. This chapter surveys ML-based methods for quantum error decoding, with a focus on topological codes and an emphasis on architectural principles, practical performance, and real-time considerations. We first frame decoding as a learning problem and outline key paradigms, including discriminative, generative, and reinforcement-learning formulations. We then introduce the neural network building blocks that underpin most contemporary neural decoders and discuss how these components can be integrated to balance expressivity, scalability, and latency. Building on this architectural perspective, we review recent progress and benchmarks in neural decoding for memory experiments, and discuss real-time decoding, open challenges, and future directions toward scalable fault-tolerant quantum computing.