mlsanityData to 14 Oct 2026

Attacks on fairness in Federated Learning

arXiv 2311.12715 ↗First posted 21 Nov 2023cs.LG cs.CRcited by 1

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Federated Learning is an important emerging distributed training paradigm that keeps data private on clients. It is now well understood that by controlling only a small subset of FL clients, it is possible to introduce a backdoor to a federated learning model, in the presence of certain attributes. In this paper, we present a new type of attack that compromises the fairness of the trained model. Fairness is understood to be the attribute-level performance distribution of a trained model. It is particularly salient in domains where, for example, skewed accuracy discrimination between subpopulations could have disastrous consequences. We find that by employing a threat model similar to that of a backdoor attack, an attacker is able to influence the aggregated model to have an unfair performance distribution between any given set of attributes. Furthermore, we find that this attack is possible by controlling only a single client. While combating naturally induced unfairness in FL has previously been discussed in depth, its artificially induced kind has been neglected. We show that defending against attacks on fairness should be a critical consideration in any situation where unfairness in a trained model could benefit a user who participated in its training.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 22 of its 35 references that are in the map. First posted on arXiv 21 Nov 2023.

Builds on

22 of 35 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  3. 2019Machine Unlearningcited by 1,061
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  6. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  8. 2019Agnostic Federated Learningcited by 456
  9. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  10. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
  11. 2019Robust Aggregation for Federated Learningcited by 317
  12. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
10 more
  1. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  2. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
  3. 2021Federated Learning: Opportunities and Challengescited by 84
  4. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 78
  5. 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 75
  6. 2021Manipulating SGD with Data Ordering Attackscited by 74
  7. 2020Poisoning Attacks on Algorithmic Fairnesscited by 59
  8. 2020Backdoor attacks and defenses in feature-partitioned collaborative learningcited by 30
  9. 2021Poisoning Attacks on Fair Machine Learningcited by 19
  10. 2022Augmentation Backdoorscited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Fairness-Constrained Optimization Attack in Federated Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness
  2. 2022Towards Multi-Objective Statistically Fair Federated Learning
  3. 2024Client-Side Patching against Backdoor Attacks in Federated Learning
  4. 2023Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
  5. 2023On the Vulnerability of Backdoor Defenses for Federated Learning
  6. 2022Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection
  7. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
  8. 2024Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape