Timezone: »

 
RVFR: Robust Vertical Federated Learning via Feature Subspace Recovery
Jing Liu · Chulin Xie · Krishnaram Kenthapadi · Sanmi Koyejo · Bo Li

@
in New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership »

Vertical Federated Learning (VFL) is a distributed learning paradigm that allows multiple agents to jointly train a global model when each agent holds a different subset of features for the same sample(s). VFL is known to be vulnerable to backdoor attacks. However, unlike the standard horizontal federated learning, improving the robustness of VFL remains challenging. To this end, we propose RVFR, a novel robust VFL training and inference framework. The key to our approach is to ensure that with a low-rank feature subspace, a small number of attacked samples, and other mild assumptions, RVFR recovers the underlying uncorrupted features with guarantees, thus sanitizes the model against a vast range of backdoor attacks. Further, RVFR also defends against inference-time adversarial feature attack. Our empirical studies further corroborate the robustness of the proposed framework.

Author Information

Jing Liu (UIUC)
Chulin Xie (University of Illinois at Urbana-Champaign)
Krishnaram Kenthapadi (Amazon)
Sanmi Koyejo (University of Illinois at Urbana-Champaign & Google Research)
Sanmi Koyejo

Sanmi Koyejo is an Assistant Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign and a research scientist at Google AI in Accra. Koyejo's research interests are in developing the principles and practice of adaptive and robust machine learning. Additionally, Koyejo focuses on applications to biomedical imaging and neuroscience. Koyejo co-founded the Black in AI organization and currently serves on its board.

Bo Li (UIUC)

More from the Same Authors