arXiv Machine Learning October 5, 2026 By Owen Friedewald, Srikar Alla, Ali Shiri Sichani, Chi-Ren Shyu

When Normalization Selects the Sign: Auditing Robustness Ablations in Quantum Attention

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 18

Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do

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.

By Md Rezwanul Islam

benchmarks

arXiv Machine Learning

Jul 14

Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

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.

By Junrui Zhang, Zemin Chen, Lusi Li, Mohammad Ghasemigol, Daniel Takabi, Rui Ning

fine-tuning

Hugging Face Trending Papers

Jul 13

Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

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.

fine-tuning

arXiv AI

Aug 20

How Quantum Is the Advantage? A Fair, Calibration- and Noise-Aware Benchmark and Attribution Audit of Quantum Machine Learning for Network Intrusion Detection

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.

By Syeda Anshrah Gillani, Mirza Samad Ahmed Baig, Shahid Munir Shah, Asher Ali, Hamzah Siddiqui

benchmarks

arXiv AI

Aug 10

Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification

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.

By Hao-Yuan Chen

llms

arXiv Machine Learning

Jun 24

Quantum Adaptive Self-Attention for Quantum Transformer Models

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.

By Chi-Sheng Chen, En-Jui Kuo

llms benchmarks

One email a morning, machine-written

Related stories

Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do

Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

How Quantum Is the Advantage? A Fair, Calibration- and Noise-Aware Benchmark and Attribution Audit of Quantum Machine Learning for Network Intrusion Detection

Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification

Quantum Adaptive Self-Attention for Quantum Transformer Models