The study investigates the vulnerability of a hybrid variational quantum classifier (VQC) used for network intrusion detection to adversarial attacks. By training on the Friday DDoS subset of CICIDS2017, the authors evaluate label‑flipping during training and FGSM evasion at prediction time, comparing results in simulation and on IBM’s Fez superconducting processor (Heron r2). They find that models with similar accuracy can differ markedly in attack resilience: a low‑confidence model loses half its detections to minor input changes, whereas a high‑confidence model requires larger perturbations to fail. Importantly, attacks crafted in simulation transfer to real hardware, and simulated device noise reduces confidence—making attacks easier—without lowering accuracy, indicating that accuracy alone does not reveal a model’s exposure.
arXiv:2608. 15617v1 Announce Type: new Abstract: Machine-learning detectors for power-system cyberattacks are themselves attack surfaces, and quantum machine learning has been proposed for them.
The study evaluates quantum machine learning (QML) models for network intrusion detection against well-tuned classical baselines across four standard datasets, using a leakage-controlled protocol and noise simulation. It introduces a quantum-attribution audit to determine whether any performance gains are truly due to quantum effects. While most tuned classical models match or surpass QML, two quantum approaches— a quantum-kernel SVM and a small hybrid circuit—show statistically significant advantages on specific metrics and tasks.
BadQubits is an LLM-based framework that statically analyzes OpenQASM 2.0 circuits before execution to detect structurally harmful patterns. The system evaluates four large language model architectures on 1,500 circuits, achieving 92.67% classification accuracy and 96.1% recall for harmful circuits with a fine‑tuned Qwen Coder 2.5 7B model. Comparative experiments show that LLMs retain sequential token structure, outperforming a bag‑of‑gates CNN, and that model decisions correlate with threat‑defining features such as SWAP density and measurement timing.
arXiv:2605.25066v2 Announce Type: replace-cross Abstract: As machine-learning workloads move onto quantum hardware they inherit a trust problem classical AI deployments have largely solved and quantu...
The paper investigates the role of quantum computing in network‑security classification through two experiments. First, it evaluates near‑term quantum‑kernel support vector machines on datasets such as KDD Cup 1999, CICIDS2017, and BoT‑IoT, finding that quantum kernels can match or sometimes improve classical baselines, though classical RBF kernels often remain stronger. Second, it explores long‑term memory efficiency using quantum oracle sketching (QOS), showing that quantum methods can achieve comparable accuracy with a smaller effective memory footprint than explicit storage, suggesting a potential advantage in memory‑efficient data access for streaming classification tasks.
The paper investigates how removing an input‑scaling module in a four‑qubit quantum‑attention detector affects both the classifier and the perturbations that reach its encoder. It shows that robustness differences can arise from the comparison rule rather than the module itself, and that altering input scales disrupts detection unless the linear classification layer is retrained. The study highlights the need to clearly define perturbation budgets, ensure attacks preserve labels, and differentiate exploratory from confirmatory tests.
The paper investigates how postprocessing routines in quantum neural network software can cause significant data loss when run on large quantum hardware. In a case study of Qiskit’s “SamplerQNN”, a filter that assumes measurement bit‑strings are in virtual qubit space removed 85–99.6% of valid shots on IBM backends, leading to unnormalised probability vectors and distorted predictions. This loss caused inference accuracy to drop from 0.94 to 0.39 and compressed training loss signals by 22–27×, severely reducing optimizer sensitivity. The authors implemented a layout‑based marginalisation fix that was merged into the library to make “SamplerQNN” forward‑compatible with current and future hardware.
arXiv:2607. 11843v1 Announce Type: cross Abstract: Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood.
arXiv:2610.09717v1 Announce Type: cross Abstract: Quantum kernel methods are leading candidates for a practical quantum advantage in machine learning, but assessing that potential requires two quanti...
arXiv:2606. 12075v1 Announce Type: cross Abstract: Network Intrusion Detection Systems (NIDS) heavily utlize Machine Learning (ML) but ML models can be manipulated via adversarial attacks.
arXiv:2608. 18572v1 Announce Type: cross Abstract: Tactile Internet services couple cyber events directly to physical actuation, so security decisions must improve risk discrimination without perturbing the control path.
Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, yet existing quantum backdoors mostly rely on a fixed trigger shared by all poisoned inputs.