mlsanityData to 14 Oct 2026

AugMixCloak: A Defense against Membership Inference Attacks via Image Transformation

arXiv 2505.07149 ↗First posted 11 May 2025cs.LGcited by 0

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

Traditional machine learning (ML) raises serious privacy concerns, while federated learning (FL) mitigates the risk of data leakage by keeping data on local devices. However, the training process of FL can still leak sensitive information, which adversaries may exploit to infer private data. One of the most prominent threats is the membership inference attack (MIA), where the adversary aims to determine whether a particular data record was part of the training set. This paper addresses this problem through a two-stage defense called AugMixCloak. The core idea is to apply data augmentation and principal component analysis (PCA)-based information fusion to query images, which are detected by perceptual hashing (pHash) as either identical to or highly similar to images in the training set. Experimental results show that AugMixCloak successfully defends against both binary classifier-based MIA and metric-based MIA across five datasets and various decentralized FL (DFL) topologies. Compared with regularization-based defenses, AugMixCloak demonstrates stronger protection. Compared with confidence score masking, AugMixCloak exhibits better generalization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 8 of its 25 references that are in the map. First posted on arXiv 11 May 2025.

Builds on

8 of 25 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction4 Jul

Other references · 7

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2017Generative Adversarial Networks: An Overviewcited by 590
  4. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  5. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 197
  6. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
  7. 2020A Secure Federated Learning Framework for 5G Networkscited by 32

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning
  2. 2026SoK: Challenges in Tabular Membership Inference Attacks
  3. 2026A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
  4. 2024Membership Inference Attacks and Defenses in Federated Learning: A Survey
  5. 2025Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
  6. 2025Cascading and Proxy Membership Inference Attacks
  7. 2022Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
  8. 2023Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study