mlsanityData to 7 Oct 2026

Fingerprint Attack: Client De-Anonymization in Federated Learning

arXiv 2310.05960 ↗First posted 12 Sep 2023cs.CR cs.AI cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another. Privacy can be further improved by ensuring that communication between the participants and the server is anonymized through a shuffle; decoupling the participant identity from their data. This paper seeks to examine whether such a defense is adequate to guarantee anonymity, by proposing a novel fingerprinting attack over gradients sent by the participants to the server. We show that clustering of gradients can easily break the anonymization in an empirical study of learning federated language models on two language corpora. We then show that training with differential privacy can provide a practical defense against our fingerprint attack.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

20 of 39 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  8. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  9. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  10. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
  11. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 163
  12. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
8 more
  1. 2022Recovering Private Text in Federated Learning of Language Modelscited by 67
  2. 2020Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairnesscited by 66
  3. 2017Prochlo: Strong Privacy for Analytics in the Crowdcited by 51
  4. 2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
  5. 2019Federated Learning of N-gram Language Modelscited by 33
  6. 2022Pretrained Models for Multilingual Federated Learningcited by 30
  7. 2020FLAME: Differentially Private Federated Learning in the Shuffle Modelcited by 27
  8. 2022Training Mixed-Domain Translation Models via Federated Learningcited by 12

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Digits micro-model for accurate and secure transactionscited by 0