mlsanityData to 7 Oct 2026

FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning

arXiv 2508.04064 ↗First posted 6 Aug 2025cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR), or a single known-trigger test. Such summaries can hide a different failure mode, in which one target label is activated by many trigger realizations. We study this failure mode with FLAT, a latent-conditioned reliability stress test for HFL backdoors. In FLAT, compromised clients still submit ordinary classifier updates to the server, while an attacker-side generator G(x,t,z) separates target intent t from trigger realization z. This separation shifts the audit question from whether one known trigger succeeds to how the hidden behavior varies across targets, latent samples, defenses, and post-stop rounds. On CIFAR-10, CIFAR-100, and Tiny-ImageNet, FLAT preserves clean utility while reaching 99.49%, 99.66%, and 94.10% single-target FedAvg ASR. The evaluation also reveals non-uniform defense responses, where a server rule can suppress one target mode while leaving another active. These observations motivate HFL backdoor audits that report target-wise ASR, worst-target ASR, target coverage, latent-sampled behavior, post-stop persistence, and defense response.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 48 references that are in the map. First posted on arXiv 6 Aug 2025.

Builds on

24 of 48 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  8. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  9. 2019Robust Aggregation for Federated Learningcited by 314
  10. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  11. 2020Input-Aware Dynamic Backdoor Attackcited by 304
  12. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
12 more
  1. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  2. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  3. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  4. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  5. 2022Marksman Backdoor: Backdoor Attacks with Arbitrary Target Classcited by 32
  6. 2023Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learningcited by 20
  7. 2024BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learningcited by 17
  8. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
  9. 2024Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learningcited by 15
  10. 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspectioncited by 13
  11. 2024Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learningcited by 3
  12. 2024Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learningcited by 1

Built on by

Not cited yet.