mlsanityData to 14 Oct 2026

Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models

arXiv 2506.17292 ↗First posted 16 Jun 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning enables collaborative learning among clients via a coordinating server while avoiding direct data sharing, offering a perceived solution to preserve privacy. However, recent studies on Membership Inference Attacks (MIAs) have challenged this notion, showing high success rates against unprotected training data. While local differential privacy (LDP) is widely regarded as a gold standard for privacy protection in data analysis, most studies on MIAs either neglect LDP or fail to provide theoretical guarantees for attack success rates against LDP-protected data. To address this gap, we derive theoretical lower bounds for the success rates of low-polynomial time MIAs that exploit vulnerabilities in fully connected or self-attention layers. We establish that even when data are protected by LDP, privacy risks persist, depending on the privacy budget. Practical evaluations on federated vision models confirm considerable privacy risks, revealing that the noise required to mitigate these attacks significantly degrades models' utility.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

27 of 49 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  7. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
  8. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  9. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  10. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 272
  11. 2017Collecting Telemetry Data Privatelycited by 149
  12. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 77
15 more
  1. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
  2. 2021Natural Language Understanding with Privacy-Preserving BERTcited by 55
  3. 2019Local Differential Privacy for Deep Learningcited by 46
  4. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  5. 2020Towards Differentially Private Text Representationscited by 29
  6. 2022Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysiscited by 29
  7. 2020A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysiscited by 26
  8. 2023Adapter is All You Need for Tuning Visual Taskscited by 19
  9. 2023Active Membership Inference Attack under Local Differential Privacy in Federated Learningcited by 17
  10. 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 17
  11. 2022Preserving Privacy and Security in Federated Learningcited by 13
  12. 2024Analysis of Privacy Leakage in Federated Large Language Modelscited by 9
  13. 2021FLSys: Toward an Open Ecosystem for Federated Learning Mobile Appscited by 6
  14. 2024Secure Aggregation is Not Private Against Membership Inference Attackscited by 6
  15. 2022Blockchain-based Secure Client Selection in Federated Learningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge
  2. 2025Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy
  3. 2026Local Layer-wise Differential Privacy in Federated Learning
  4. 2026Leveraging Membership Inference Attacks for Privacy Measurement in Federated Learning for Remote Sensing Images
  5. 2024Federated Learning Nodes Can Reconstruct Peers' Image Data
  6. 2024Membership Information Leakage in Federated Contrastive Learning
  7. 2022Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
  8. 2025FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates