"A Comprehensive Quantum Attack Dataset (QAD)"

Read full text Summarise with VIRAT
Authors: Pasindu Udugahapattuwa, Chamitha de Alwis, Uditha Wijewardhana, Madhusanka Liyanage
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

"The Quantum Attack Dataset (QAD) is a publicly available resource designed to support reproducible research on quantum intrusion detection by providing large-scale, systematically generated quantum attack scenarios in a simulated multi-tenant quantum execution environment. QAD models seven attack types\u2014swap injection, gate insertion, depolarizing noise, amplitude damping, measurement tampering, pulse-level attacks, and thermal relaxation\u2014capturing threats relevant to NISQ-era devices and shared quantum cloud stacks. The dataset is released in two coordinated views: a defender-oriented feature set derived from circuit structure and measurement statistics, and a complementary metadata view containing attack and noise parameters, hardware-inspired profiles, and configuration details, enabling controlled studies while avoiding label leakage. Two 1-million-sample corpora are provided: a balanced version for method development and ablation, and an unbalanced version that encodes operationally motivated attack frequencies using empirically derived imbalance ratios. Alongside the data, we supply baseline results from four machine learning models (DB-NN, Random Forest, XGBoost, LightGBM) to illustrate that the released features support effective classification in both balanced and imbalanced regimes. All data files, schemas, and generation scripts are hosted in a persistent repository with rich metadata, documented quality checks, and usage guidelines to facilitate discovery, reuse, and extension of QAD for future quantum-security and quantum-safe defense studies."

Fields of Study & Subjects

Quantum Computing Algorithms and Architecture Quantum Information and Cryptography Adversarial Robustness in Machine Learning

Publication details

Journal / source
IEEE DataPort
Publication date
26 March 2026
Language
EN
Document type
Dataset