mlsanityData to 14 Oct 2026

Security and Privacy Issues of Federated Learning

arXiv 2307.12181 ↗First posted 22 Jul 2023cs.CR cs.AIcited by 2

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

Abstract (arXiv)

Federated Learning (FL) has emerged as a promising approach to address data privacy and confidentiality concerns by allowing multiple participants to construct a shared model without centralizing sensitive data. However, this decentralized paradigm introduces new security challenges, necessitating a comprehensive identification and classification of potential risks to ensure FL's security guarantees. This paper presents a comprehensive taxonomy of security and privacy challenges in Federated Learning (FL) across various machine learning models, including large language models. We specifically categorize attacks performed by the aggregator and participants, focusing on poisoning attacks, backdoor attacks, membership inference attacks, generative adversarial network (GAN) based attacks, and differential privacy attacks. Additionally, we propose new directions for future research, seeking innovative solutions to fortify FL systems against emerging security risks and uphold sensitive data confidentiality in distributed learning environments.

Key facts. Cited by 2 papers 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 14 of its 24 references that are in the map. First posted on arXiv 22 Jul 2023.

Builds on

14 of 24 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Subject Membership Inference Attacks in Federated Learning7 Jun

Other references · 13

  1. 2018How To Backdoor Federated Learningcited by 765
  2. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  3. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  4. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  5. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  6. 2019Can You Really Backdoor Federated Learning?cited by 255
  7. 2018Differentially Private Generative Adversarial Networkcited by 235
  8. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  9. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  10. 2019Generative Models for Effective ML on Private, Decentralized Datasetscited by 85
  11. 2018Towards Demystifying Membership Inference Attackscited by 40
  12. 2020More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligencecited by 23
1 more
  1. 2019Scalable and Differentially Private Distributed Aggregation in the Shuffled Modelcited by 20

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2025Securing Genomic Data Against Inference Attacks in Federated Learning Environmentscited by 1
  2. 2024Navigating the Future of Federated Recommendation Systems with Foundation Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Federated Learning: Attacks, Defenses, Opportunities, and Challenges
  2. 2022Federated Learning: Balancing the Thin Line Between Data Intelligence and Privacy
  3. 2024Defending against Data Poisoning Attacks in Federated Learning via User Elimination
  4. 2024GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning
  5. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
  6. 2023Privacy Inference-Empowered Stealthy Backdoor Attack on Federated Learning under Non-IID Scenarios
  7. 2021Meta Federated Learning
  8. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions