Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning

Zhixuan Ma, Haichang Gao, Shangwen Li, Ping Wang, Han Yu
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:84371-84388, 2026.

Abstract

Federated learning (FL) is vulnerable to backdoor attacks. Yet sustaining backdoor effectiveness under repeated aggregation remains challenging. Existing methods often rely on heuristic trigger designs or indiscriminant parameter manipulation, leading to rapid decay or detectable anomalies. In this work, we view FL backdoor persistence through the lens of optimization dynamics, and argue that long-lasting attacks require alignment between trigger-induced representations and aggregation-stable parameter directions. Based on this insight, we propose the Coupled Trigger Optimization and Vulnerable Parameter Alignment (CTO-VPA) FL backdoor attack method. By constraining updates to this coupled subspace, backdoor behaviors can be embedded into optimization-stable directions while preserving benign performance. Experiments across multiple datasets and defense settings show that CTO-VPA achieves substantially improved persistence and robustness compared to prior attacks, highlighting the importance of trigger–parameter coupling in FL settings. The code is available at https://github.com/SwLi415/COVERT.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-ma26k, title = {Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning}, author = {Ma, Zhixuan and Gao, Haichang and Li, Shangwen and Wang, Ping and Yu, Han}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {84371--84388}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/ma26k/ma26k.pdf}, url = {https://proceedings.mlr.press/v306/ma26k.html}, abstract = {Federated learning (FL) is vulnerable to backdoor attacks. Yet sustaining backdoor effectiveness under repeated aggregation remains challenging. Existing methods often rely on heuristic trigger designs or indiscriminant parameter manipulation, leading to rapid decay or detectable anomalies. In this work, we view FL backdoor persistence through the lens of optimization dynamics, and argue that long-lasting attacks require alignment between trigger-induced representations and aggregation-stable parameter directions. Based on this insight, we propose the Coupled Trigger Optimization and Vulnerable Parameter Alignment (CTO-VPA) FL backdoor attack method. By constraining updates to this coupled subspace, backdoor behaviors can be embedded into optimization-stable directions while preserving benign performance. Experiments across multiple datasets and defense settings show that CTO-VPA achieves substantially improved persistence and robustness compared to prior attacks, highlighting the importance of trigger–parameter coupling in FL settings. The code is available at https://github.com/SwLi415/COVERT.} }
Endnote
%0 Conference Paper %T Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning %A Zhixuan Ma %A Haichang Gao %A Shangwen Li %A Ping Wang %A Han Yu %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-ma26k %I PMLR %P 84371--84388 %U https://proceedings.mlr.press/v306/ma26k.html %V 306 %X Federated learning (FL) is vulnerable to backdoor attacks. Yet sustaining backdoor effectiveness under repeated aggregation remains challenging. Existing methods often rely on heuristic trigger designs or indiscriminant parameter manipulation, leading to rapid decay or detectable anomalies. In this work, we view FL backdoor persistence through the lens of optimization dynamics, and argue that long-lasting attacks require alignment between trigger-induced representations and aggregation-stable parameter directions. Based on this insight, we propose the Coupled Trigger Optimization and Vulnerable Parameter Alignment (CTO-VPA) FL backdoor attack method. By constraining updates to this coupled subspace, backdoor behaviors can be embedded into optimization-stable directions while preserving benign performance. Experiments across multiple datasets and defense settings show that CTO-VPA achieves substantially improved persistence and robustness compared to prior attacks, highlighting the importance of trigger–parameter coupling in FL settings. The code is available at https://github.com/SwLi415/COVERT.
APA
Ma, Z., Gao, H., Li, S., Wang, P. & Yu, H.. (2026). Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:84371-84388 Available from https://proceedings.mlr.press/v306/ma26k.html.

Related Material