mlsanityData to 7 Oct 2026

Defending Model Inversion and Membership Inference Attacks via Prediction Purification

arXiv 2005.03915 ↗First posted 8 May 2020cs.CR cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence scores predicted by the target classifier. In this paper, we propose a unified approach, namely purification framework, to defend data inference attacks. It purifies the confidence score vectors predicted by the target classifier by reducing their dispersion. The purifier can be further specialized in defending a particular attack via adversarial learning. We evaluate our approach on benchmark datasets and classifiers. We show that when the purifier is dedicated to one attack, it naturally defends the other one, which empirically demonstrates the connection between the two attacks. The purifier can effectively defend both attacks. For example, it can reduce the membership inference accuracy by up to 15% and increase the model inversion error by a factor of up to 4. Besides, it incurs less than 0.4% classification accuracy drop and less than 5.5% distortion to the confidence scores.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 11; 2023: 2; 2024: 10; 2025: 1; 2026: 3.

32 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  2. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecturecited by 63
  3. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  4. 2022Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Modelscited by 42
  5. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  6. 2024Evaluations of Machine Learning Privacy Defenses are Misleadingcited by 35
  7. 2022Bilateral Dependency Optimization: Defending Against Model-inversion Attackscited by 30
  8. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  9. 2022One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacycited by 26
  10. 2023Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Predictioncited by 26
  11. 2024Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometricscited by 12
  12. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
20 more
  1. 2021Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspectivecited by 10
  2. 2022On the utility and protection of optimization with differential privacy and classic regularization techniquescited by 10
  3. 2022SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discriminationcited by 7
  4. 2022Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacycited by 7
  5. 2022MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Memberscited by 6
  6. 2024MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defensecited by 5
  7. 2022Label-only Model Inversion Attack: The Attack that Requires the Least Informationcited by 4
  8. 2023Introducing Model Inversion Attacks on Automatic Speaker Recognitioncited by 4
  9. 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attackscited by 4
  10. 2024Deep Learning Model Security: Threats and Defensescited by 4
  11. 2022Privacy-preserving Generative Framework Against Membership Inference Attackscited by 3
  12. 2021Preserving Privacy in Personalized Models for Distributed Mobile Servicescited by 2
  13. 2022LDL: A Defense for Label-Based Membership Inference Attackscited by 1
  14. 2024Inference Attacks Against Face Recognition Model without Classification Layerscited by 1
  15. 2024Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attackscited by 1
  16. 2024Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attackscited by 0
  17. 2025PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attackscited by 0
  18. 2026Private and interpretable clinical prediction with quantum-inspired tensor train modelscited by 0
  19. 2026LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settingscited by 0
  20. 2026Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matchingcited by 0