mlsanityData to 14 Oct 2026

Unveiling Hidden Threats: Using Fractal Triggers to Boost Stealthiness of Distributed Backdoor Attacks in Federated Learning

arXiv 2511.09252 ↗First posted 12 Nov 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Traditional distributed backdoor attacks (DBA) in federated learning improve stealthiness by decomposing global triggers into sub-triggers, which however requires more poisoned data to maintian the attck strength and hence increases the exposure risk. To overcome this defect, This paper proposes a novel method, namely Fractal-Triggerred Distributed Backdoor Attack (FTDBA), which leverages the self-similarity of fractals to enhance the feature strength of sub-triggers and hence significantly reduce the required poisoning volume for the same attack strength. To address the detectability of fractal structures in the frequency and gradient domains, we introduce a dynamic angular perturbation mechanism that adaptively adjusts perturbation intensity across the training phases to balance efficiency and stealthiness. Experiments show that FTDBA achieves a 92.3% attack success rate with only 62.4% of the poisoning volume required by traditional DBA methods, while reducing the detection rate by 22.8% and KL divergence by 41.2%. This study presents a low-exposure, high-efficiency paradigm for federated backdoor attacks and expands the application of fractal features in adversarial sample generation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 12 Nov 2025.

Builds on

22 of 42 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  3. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  4. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  5. 2018Spectral Signatures in Backdoor Attackscited by 484
  6. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  7. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  8. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  9. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 324
  10. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  11. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  12. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 263
10 more
  1. 2019Can You Really Backdoor Federated Learning?cited by 255
  2. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 161
  3. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
  4. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  5. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
  6. 2023Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistencycited by 46
  7. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  8. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  9. 2022A Primal-Dual Algorithm for Hybrid Federated Learningcited by 4
  10. 2024Poisoning with A Pill: Circumventing Detection in Federated Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning
  2. 2026Fine-grained Distributed Backdoor Attacks in Federated Learning
  3. 2026Structure-Aware Distributed Backdoor Attacks in Federated Learning
  4. 2025Multi-Target Federated Backdoor Attack Based on Feature Aggregation
  5. 2024Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape
  6. 2023On the Vulnerability of Backdoor Defenses for Federated Learning
  7. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
  8. 2026Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective