mlsanityData to 7 Oct 2026

BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning

arXiv 2405.20862 ↗First posted 31 May 2024cs.CRcited by 17

Not on the map. Why?

Abstract (arXiv)

In a federated learning (FL) system, decentralized data owners (clients) could upload their locally trained models to a central server, to jointly train a global model. Malicious clients may plant backdoors into the global model through uploading poisoned local models, causing misclassification to a target class when encountering attacker-defined triggers. Existing backdoor defenses show inconsistent performance under different system and adversarial settings, especially when the malicious updates are made statistically close to the benign ones. In this paper, we first reveal the fact that planting subsequent backdoors with the same target label could significantly help to maintain the accuracy of previously planted backdoors, and then propose a novel proactive backdoor detection mechanism for FL named BackdoorIndicator, which has the server inject indicator tasks into the global model leveraging out-of-distribution (OOD) data, and then utilizing the fact that any backdoor samples are OOD samples with respect to benign samples, the server, who is completely agnostic of the potential backdoor types and target labels, can accurately detect the presence of backdoors in uploaded models, via evaluating the indicator tasks. We perform systematic and extensive empirical studies to demonstrate the consistently superior performance and practicality of BackdoorIndicator over baseline defenses, across a wide range of system and adversarial settings.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 May 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 12; 2026: 4.

17 papers.

Sort:

By area:

  1. 2025MARS: A Malignity-Aware Backdoor Defense in Federated Learningcited by 7
  2. 2025DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Datacited by 5
  3. 2024Identify Backdoored Model in Federated Learning via Individual Unlearningcited by 4
  4. 2025Toward Malicious Clients Detection in Federated Learningcited by 4
  5. 2025Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learningcited by 1
  6. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learningcited by 1
  7. 2025On the Out-of-Distribution Backdoor Attack for Federated Learningcited by 1
  8. 2025DEFEND: Poisoned Model Detection and Malicious Client Exclusion Mechanism for Secure Federated Learning-based Road Condition Classificationcited by 1
  9. 2026Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learningcited by 1
  10. 2025TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Datacited by 0
  11. 2025On the Inference (In-)Security of Vertical Federated Learning: Efficient Auditing against Inference Tampering Attackcited by 0
  12. 2025FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learningcited by 0
5 more
  1. 2025FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learningcited by 0
  2. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinctioncited by 0
  3. 2026FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learningcited by 0
  4. 2026SecureAFL: Secure Asynchronous Federated Learningcited by 0
  5. 2026Securing Autonomous Vehicle Systems via Twin-Aware Federated Reinforcement Learningcited by 0