Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2506.21842 · Quantum science and technology

Adversarial Threats in Quantum Machine Learning: A Survey of Attacks and Defenses

Archisman Ghosh, Satwik Kundu, Swaroop Ghosh

Published Jan 1, 2026• 6 citations
arXivHTMLPDF
DOI
10.1007/978-3-032-11153-1_3

Related papers

Quantum Adversarial Machine Learning and Defense Strategies: Challenges and Opportunities

Eric Yocam, Anthony Rizi, Mahesh Kamepalli +3 more

arXiv:2412.12373•Quantum science and technology•Jan 1, 2026•10 citations

Quantum adversarial machine learning: from classical adaptations to quantum-native methods

Roozbeh Razavi‐Far, Mohammad Meymani, Erfan Mahmoudinia +6 more

Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulnerabilities to build robust machine learning models. Quantum machine learning is an interdisciplinary field that bridges quantum computing and classical machine learning. While quantum machine learning shows potentials to outperform classical machine learning in complex tasks such as regression, classification, and generative modeling, it remains vulnerable to adversarial attacks. Given the recent advancements in quantum computing and machine learning, the quantum adversarial machine learning field has emerged to study the vulnerabilities of quantum machine learning, possible attacks, and novel quantum-enhanced defense strategies. In this survey, we provide a detailed overview on quantum adversarial machine learning and explore the existing attacks and countermeasures. We also review the theoretical underpinnings of this area, emerging trends, and critical challenges.

arXiv:2605.18821•Artificial Intelligence Review•May 11, 2026•4 citations

Subject Review:AI-Driven Security in Quantum Machine Learning:Vulnerabilities,Threats, and Defenses

Farah Neamah Abbas, Mohanad Ridha Ghanim, Rafal Naser Saleh

Quantum Machine Learning (QML) has advanced significantly thanks to the combination of Quantum Computing (QC) with Artificial Intelligence (AI), hence releasing computational benefits over conventional methods. This synergy does, however, also bring fresh security flaws like adversarial attacks, quantum noise manipulation, and cryptographic weaknesses. This work offers a thorough investigation of QML security along with an examination of its special vulnerabilities resulting from hardware-induced faults, quantum variational circuits, and quantum data encoding. We methodically investigate adversarial attack techniques using the probabilistic character of quantum states including side-channel assaults, quantum noise injection, and algorithmic perturbations. We also assess innovative defensive strategies such differential privacy, quantum adversarial training, quantum error correction (QEC), cryptographic techniques include Quantum Homomorphic Encryption (QHE), We offer a hybrid AI-driven method for protecting QML models against developing threats by linking artificial intelligence and quantum security frameworks. This work emphasizes the importance of developing quantum-safe AI systems and consistent adversarial robustness standards. The results help to advance AI-enhanced quantum security, thereby guaranteeing the future of QML applications is efficient, strong, and resistant to adversarial attack.

International Journal of Engineering Research and Advanced Technology•Jan 1, 2025•0 citations

Adversarial Robustness in Quantum Machine Learning

Nicola Franco, Aman Saxena, Tom Wollschläger +3 more

Quantum science and technology•Jan 1, 2026•0 citations

Emerging Attack Strategies Against Quantum Key Distribution Systems: A Comprehensive Survey of Protocols, Attacks and Mitigation Strategies

Suman Palrecha, Shashwat Saxena, Avinash Upadhyay +4 more

Quantum key distribution (QKD) is widely regarded as a highly secure quantum encryption approach since it applies theoretical principles of quantum mechanics as a medium of security, unlike classical encryption processes that rely on complex mathematics. However, practical QKD systems are vulnerable due to imperfect photon source hardware, communication channel, and detector implementation. These hardware imperfections open side channels that an adversary can exploit without violating principles of quantum mechanics. This review provides a comprehensive overview of the current QKD protocols, quantum hacking strategies and their operating principles, vulnerable hardware components and their mitigation techniques. This paper further investigates how state-of-the-art paradigms based on artificial intelligence (AI) and machine learning (ML), along with key subfields—such as deep learning (DL), deep reinforcement learning (DRL), and quantum machine learning (QML)—are reshaping the domain. In particular, this paper analyzes their dual roles as enablers of sophisticated attacks and as instruments for attack detection and mitigation. By jointly addressing the challenges in quantum communication and adaptive learning, as well as attack and detection architectures, this survey elucidates both the capabilities and the limitations of contemporary attack-detection mechanisms in the field. This survey seeks to establish a unified framework that conceptually integrates physical-layer quantum hacking with AI-/ML-based security, emphasizing their dual function as both an intelligent defensive layer and a potential tool for advanced threats.

Lights•Oct 28, 2026•0 citations

Towards quantum enhanced adversarial robustness in machine learning

Maxwell T. West, Shu-Lok Tsang, Jia Shun Low +5 more

arXiv:2306.12688•Nature Machine Intelligence•May 25, 2023•98 citations
Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulnerabilities to build robust machine learning models. Quantum machine learning is an interdisciplinary field that bridges quantum computing and classical machine learning. While quantum machine learning shows potentials to outperform classical machine learning in complex tasks such as regression, classification, and generative modeling, it remains vulnerable to adversarial attacks. Given the recent advancements in quantum computing and machine learning, the quantum adversarial machine learning field has emerged to study the vulnerabilities of quantum machine learning, possible attacks, and novel quantum-enhanced defense strategies. In this survey, we provide a detailed overview on quantum adversarial machine learning and explore the existing attacks and countermeasures. We also review the theoretical underpinnings of this area, emerging trends, and critical challenges.
Quantum Machine Learning (QML) has advanced significantly thanks to the combination of Quantum Computing (QC) with Artificial Intelligence (AI), hence releasing computational benefits over conventional methods. This synergy does, however, also bring fresh security flaws like adversarial attacks, quantum noise manipulation, and cryptographic weaknesses. This work offers a thorough investigation of QML security along with an examination of its special vulnerabilities resulting from hardware-induced faults, quantum variational circuits, and quantum data encoding. We methodically investigate adversarial attack techniques using the probabilistic character of quantum states including side-channel assaults, quantum noise injection, and algorithmic perturbations. We also assess innovative defensive strategies such differential privacy, quantum adversarial training, quantum error correction (QEC), cryptographic techniques include Quantum Homomorphic Encryption (QHE), We offer a hybrid AI-driven method for protecting QML models against developing threats by linking artificial intelligence and quantum security frameworks. This work emphasizes the importance of developing quantum-safe AI systems and consistent adversarial robustness standards. The results help to advance AI-enhanced quantum security, thereby guaranteeing the future of QML applications is efficient, strong, and resistant to adversarial attack.
Quantum key distribution (QKD) is widely regarded as a highly secure quantum encryption approach since it applies theoretical principles of quantum mechanics as a medium of security, unlike classical encryption processes that rely on complex mathematics. However, practical QKD systems are vulnerable due to imperfect photon source hardware, communication channel, and detector implementation. These hardware imperfections open side channels that an adversary can exploit without violating principles of quantum mechanics. This review provides a comprehensive overview of the current QKD protocols, quantum hacking strategies and their operating principles, vulnerable hardware components and their mitigation techniques. This paper further investigates how state-of-the-art paradigms based on artificial intelligence (AI) and machine learning (ML), along with key subfields—such as deep learning (DL), deep reinforcement learning (DRL), and quantum machine learning (QML)—are reshaping the domain. In particular, this paper analyzes their dual roles as enablers of sophisticated attacks and as instruments for attack detection and mitigation. By jointly addressing the challenges in quantum communication and adaptive learning, as well as attack and detection architectures, this survey elucidates both the capabilities and the limitations of contemporary attack-detection mechanisms in the field. This survey seeks to establish a unified framework that conceptually integrates physical-layer quantum hacking with AI-/ML-based security, emphasizing their dual function as both an intelligent defensive layer and a potential tool for advanced threats.