mlsanityData to 7 Oct 2026

Knowledge-Enriched Distributional Model Inversion Attacks

arXiv 2010.04092 ↗First posted 8 Oct 2020cs.LGcited by 65

Not on the map. Why?

Abstract (arXiv)

Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing MI attacks against deep neural networks (DNNs) have large room for performance improvement. We present a novel inversion-specific GAN that can better distill knowledge useful for performing attacks on private models from public data. In particular, we train the discriminator to differentiate not only the real and fake samples but the soft-labels provided by the target model. Moreover, unlike previous work that directly searches for a single data point to represent a target class, we propose to model a private data distribution for each target class. Our experiments show that the combination of these techniques can significantly boost the success rate of the state-of-the-art MI attacks by 150%, and generalize better to a variety of datasets and models. Our code is available at https://github.com/SCccc21/Knowledge-Enriched-DMI.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 19; 2024: 18; 2025: 13; 2026: 6.

65 papers.

Sort:

By area:

  1. 2022Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attackscited by 58
  2. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  3. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  4. 2023Re-thinking Model Inversion Attacks Against Deep Neural Networkscited by 39
  5. 2023Reinforcement Learning-Based Black-Box Model Inversion Attackscited by 33
  6. 2022Bilateral Dependency Optimization: Defending Against Model-inversion Attackscited by 30
  7. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  8. 2023Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Networkcited by 28
  9. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  10. 2023Label-Only Model Inversion Attacks via Knowledge Transfercited by 21
  11. 2024A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attackscited by 17
  12. 2023On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximationcited by 16
38 more
  1. 2023Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyondcited by 14
  2. 2023Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Modelcited by 14
  3. 2023Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attackscited by 12
  4. 2024Model Inversion Robustness: Can Transfer Learning Help?cited by 11
  5. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  6. 2024Model Inversion Attacks Through Target-Specific Conditional Diffusion Modelscited by 8
  7. 2024On the Vulnerability of Skip Connections to Model Inversion Attackscited by 8
  8. 2022Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT datacited by 7
  9. 2022SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discriminationcited by 7
  10. 2023Boosting Model Inversion Attacks with Adversarial Examplescited by 7
  11. 2023DANAA: Towards transferable attacks with double adversarial neuron attributioncited by 7
  12. 2024BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attackscited by 7
  13. 2023Model Inversion Attack via Dynamic Memory Learningcited by 6
  14. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  15. 2024CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversioncited by 6
  16. 2022Roadmap for Cybersecurity in Autonomous Vehiclescited by 5
  17. 2024Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?cited by 5
  18. 2024MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defensecited by 5
  19. 2025SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmarkcited by 5
  20. 2023Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Modelscited by 4
  21. 2023All Rivers Run to the Sea: Private Learning with Asymmetric Flowscited by 4
  22. 2024Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filteringcited by 4
  23. 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attackscited by 4
  24. 2025From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challengescited by 4
  25. 2025LeakyCLIP: Extracting Training Data from CLIPcited by 4
  26. 2022FedComm: Federated Learning as a Medium for Covert Communicationcited by 3
  27. 2022Data Stealing Attack on Medical Images: Is it Safe to Export Networks from Data Lakes?cited by 2
  28. 2023Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulationscited by 2
  29. 2024Direct Acquisition Optimization for Low-Budget Active Learningcited by 2
  30. 2024Prediction Exposes Your Face: Black-box Model Inversion via Prediction Alignmentcited by 2
  31. 2024Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?cited by 2
  32. 2025A Sample-Level Evaluation and Generative Framework for Model Inversion Attackscited by 2
  33. 2024Distributional Black-Box Model Inversion Attack with Multi-Agent Reinforcement Learningcited by 1
  34. 2025Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessmentcited by 1
  35. 2025Generative Model Inversion Through the Lens of the Manifold Hypothesiscited by 1
  36. 2026Guarding the Middle: Protecting Intermediate Representations in Federated Split Learningcited by 1
  37. 2026AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspectivecited by 1
  38. 2022Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversioncited by 0

50 most cited of 65 All 65 (JSON)