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.
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.
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.
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.
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.
arXiv:2608. 06846v1 Announce Type: cross Abstract: We test whether a parameterized quantum circuit (PQC) improves a hybrid quantum-classical model's performance on classical datasets, using an interface-matched classical map as the control while holding all other components fixed.
arXiv:2504. 05336v4 Announce Type: replace-cross Abstract: A recurring weakness in quantum machine learning (QML) is that reported ``quantum advantages'' are seldom tested against a \emph{capacity-matched} classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it.
arXiv:2604. 10933v2 Announce Type: replace-cross Abstract: Deep neural networks remain highly vulnerable to adversarial perturbations, limiting their reliability in security- and safety-critical applications.
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: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...
The paper proposes Entanglement-Weighted Pruning (EWP), a method for unlearning a client’s contribution from a federated quantum classifier without retraining from scratch. EWP scores each trainable circuit parameter by combining a Fisher‑information estimate on the target client’s data with a structural entanglement weight, pruning the lowest‑scoring parameters and optionally fine‑tuning the remaining ones. Experiments on a four‑qubit data‑re‑uploading ansatz trained with FedAvg across five simulated supply‑chain‑risk clients show that EWP achieves accuracy comparable to full retraining while reducing forgetting and wall‑clock time by about sixteenfold, outperforming random, Fisher‑only, or entanglement‑only pruning.
arXiv:2610.09635v1 Announce Type: cross Abstract: Anomaly detection on small and unbalanced datasets remains very challenging in machine learning, although this scenario is common in several domains,...
arXiv:2608. 05240v1 Announce Type: cross Abstract: One-bit post-training quantization represents each weight using only its sign, requiring all deployment contexts to share the same binary weight matrix even when their activation statistics favor different sign patterns.