mlsanityData to 14 Oct 2026

Watch Out for the Lifespan: Evaluating Backdoor Attacks Against Federated Model Adaptation

arXiv 2511.14406 ↗First posted 18 Nov 2025cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Large models adaptation through Federated Learning (FL) addresses a wide range of use cases and is enabled by Parameter-Efficient Fine-Tuning techniques such as Low-Rank Adaptation (LoRA). However, this distributed learning paradigm faces several security threats, particularly to its integrity, such as backdoor attacks that aim to inject malicious behavior during the local training steps of certain clients. We present the first analysis of the influence of LoRA on state-of-the-art backdoor attacks targeting model adaptation in FL. Specifically, we focus on backdoor lifespan, a critical characteristic in FL, that can vary depending on the attack scenario and the attacker's ability to effectively inject the backdoor. A key finding in our experiments is that for an optimally injected backdoor, the backdoor persistence after the attack is longer when the LoRA's rank is lower. Importantly, our work highlights evaluation issues of backdoor attacks against FL and contributes to the development of more robust and fair evaluations of backdoor attacks, enhancing the reliability of risk assessments for critical FL systems. Our code is publicly available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

17 of 23 references.

References · 17

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  4. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  5. 2018How To Backdoor Federated Learningcited by 765
  6. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  7. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  8. 2024PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Modelscited by 269
  9. 2019Can You Really Backdoor Federated Learning?cited by 255
  10. 2024Improving LoRA in Privacy-preserving Federated Learningcited by 161
  11. 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptationscited by 146
  12. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
5 more
  1. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 94
  2. 2024A Survey on LoRA of Large Language Modelscited by 67
  3. 2023On the Vulnerability of Backdoor Defenses for Federated Learningcited by 27
  4. 2024LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystemcited by 24
  5. 2024LoBAM: LoRA-Based Backdoor Attack on Model Mergingcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips
  2. 2025TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
  3. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning
  4. 2025Hammer and Anvil: Toward a Theory of Backdoors in Federated Learning
  5. 2024Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
  6. 2022Technical Report: Assisting Backdoor Federated Learning with Whole Population Knowledge Alignment
  7. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
  8. 2024FLAIN: Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons