Entangled Threats: A Unified Kill Chain Model for Quantum Machine Learning Security

Salvato in:
Dettagli Bibliografici
Pubblicato in:The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 1653-1664
Autore principale: Debus, Pascal
Altri autori: Wendlinger, Maximilian, Kilian Tscharke, Herr, Daniel, Brugmann, Cedric, Ohl De Mello, Daniel, Ulmanis, Juris, Alexander, Erhard, Schmidt, Arthur, Petsch, Fabian
Pubblicazione:
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Soggetti:
Accesso online:Citation/Abstract
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!

MARC

LEADER 00000nab a2200000uu 4500
001 3278707014
003 UK-CbPIL
024 7 |a 10.1109/QCE65121.2025.00183  |2 doi 
035 |a 3278707014 
045 2 |b d20250101  |b d20251231 
084 |a 228229  |2 nlm 
100 1 |a Debus, Pascal  |u Fraunhofer Institute for Applied and Integrated Security (AISEC),Garching near Munich,Germany 
245 1 |a Entangled Threats: A Unified Kill Chain Model for Quantum Machine Learning Security 
260 |b The Institute of Electrical and Electronics Engineers, Inc. (IEEE)  |c 2025 
513 |a Conference Proceedings 
520 3 |a Conference Title: 2025 IEEE International Conference on Quantum Computing and Engineering (QCE)Conference Start Date: 2025 Aug. 30Conference End Date: 2025 Sept. 5Conference Location: Albuquerque, NM, USAQuantum Machine Learning (QML) systems inherit vulnerabilities from classical machine learning while introducing new attack surfaces rooted in the physical and algorithmic layers of quantum computing. Despite a growing body of research on individual attack vectors - ranging from adversarial poisoning and evasion to circuit-level backdoors, side-channel leakage, and model extraction - these threats are often analyzed in isolation, with unrealistic assumptions about attacker capabilities and system environments. This fragmentation hampers the development of effective, holistic defense strategies. In this work, we argue that QML security requires more structured modeling of the attack surface, capturing not only individual techniques but also their relationships, prerequisites, and potential impact across the QML pipeline. We propose adapting kill chain models, widely used in classical IT and cybersecurity, to the quantum machine learning context. Such models allow for structured reasoning about attacker objectives, capabilities, and possible multi-stage attack paths - spanning reconnaissance, initial access, manipulation, persistence, and exfiltration. Based on extensive literature analysis, we present a detailed taxonomy of QML attack vectors mapped to corresponding stages in a quantum-aware kill chain framework that is inspired by the MITRE ATLAS for classical machine learning. We highlight interdependencies between physical-level threats (like side-channel leakage and crosstalk faults), data and algorithm manipulation (such as poisoning or circuit backdoors), and privacy attacks (including model extraction and training data inference). This work provides a foundation for more realistic threat modeling and proactive security-in-depth design in the emerging field of quantum machine learning. 
653 |a Machine learning 
653 |a Quantum computing 
653 |a Poisoning 
653 |a Taxonomy 
653 |a Threat evaluation 
653 |a Threat models 
653 |a Leakage 
653 |a Cybersecurity 
653 |a Crosstalk 
653 |a Economic 
700 1 |a Wendlinger, Maximilian  |u Fraunhofer Institute for Applied and Integrated Security (AISEC),Garching near Munich,Germany 
700 1 |a Kilian Tscharke  |u Fraunhofer Institute for Applied and Integrated Security (AISEC),Garching near Munich,Germany 
700 1 |a Herr, Daniel  |u d-fine (GmbH),Frankfurt,Germany 
700 1 |a Brugmann, Cedric  |u d-fine (GmbH),Frankfurt,Germany 
700 1 |a Ohl De Mello, Daniel  |u d-fine (GmbH),Frankfurt,Germany 
700 1 |a Ulmanis, Juris  |u Alpine Quantum Technologies (AQT) GmbH,Innsbruck,Austria 
700 1 |a Alexander, Erhard  |u Alpine Quantum Technologies (AQT) GmbH,Innsbruck,Austria 
700 1 |a Schmidt, Arthur  |u Federal Office for Information Security (BSI),Bonn,Germany 
700 1 |a Petsch, Fabian  |u Federal Office for Information Security (BSI),Bonn,Germany 
773 0 |t The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings  |g (2025), p. 1653-1664 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3278707014/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch