{"type":"ScholarlyArticle","title":"Can Quantum Federated Learning Withstand Circuit-Level Backdoors?","authors":[{"name":"Aakar Mathur","slug":"aakar-mathur","given":"Aakar","family":"Mathur","affiliation":""},{"name":"Ruknuddin Mohammed","slug":"ruknuddin-mohammed","given":"Ruknuddin","family":"Mohammed","affiliation":""},{"name":"Ashish Gupta","slug":"ashish-gupta","given":"Ashish","family":"Gupta","affiliation":""}],"abstract":"Quantum Federated Learning (QFL) inherits the core vulnerability of federated optimization to malicious clients, while also introducing an attack surface from variational circuit training and measurement-driven gradients. This work proposes a novel CircUit-Level backdoor Threat (CULT) model that formalizes four stealthy attacks by exploiting quantum-aware mechanisms, including Grover, Pauli, Bit-flip, and Sign-flip. By enabling malicious clients on both in-training and post-training surfaces, these attacks can critically undermine the learning process. We establish a rigorous theoretical foundation to demonstrate attack stealthiness under standard smoothness assumptions. Experiments on the MNIST and CIFAR-10 datasets with non-IID splits and varying fractions of malicious clients show that even a single malicious client can induce severe accuracy degradation under FedAvg aggregation. While popular defenses, including Krum, Multi-Krum, FoolsGold, FLGuardian, and Mud-HoG, reduce degradation in many regimes, they fail to eliminate worst-case failure cases, where accuracy drops up to 50%. The experimental analysis further reveals that under the CULT model, malicious updates effectively mask their presence by staying close to benign norms, thereby helping attackers evade detection.","doi":"10.24963/ijcai.2026/518","url":"https://ijcai.org/proceedings/2026/518","pdf":"https://ijcai.org/proceedings/2026/0518.pdf","markdown":"https://ijcai.org/proceedings/2026/518.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/518","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":518,"pages":{"first":4651,"last":4659},"keywords":["Machine Learning: Federated learning","Machine Learning: Classification"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}