mlsanityData to 14 Oct 2026

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense

arXiv 2410.05159 ↗First posted 7 Oct 2024cs.CV cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the privacy vulnerabilities of Deep Neural Networks (DNNs). Unfortunately, in tandem with the rapid evolution of MI attacks, the absence of a comprehensive benchmark with standardized metrics and reproducible implementations has emerged as a formidable challenge. This deficiency has hindered objective comparison of methodological advancements and reliable assessment of defense efficacy. To address this critical gap, we build the first practical benchmark named MIBench for systematic evaluation of model inversion attacks and defenses. This benchmark bases on an extensible and reproducible modular-based toolbox which currently integrates a total of 19 state-of-the-art attack and defense methods and encompasses 9 standardized evaluation protocols. Capitalizing on this foundation, we conduct extensive evaluation from multiple perspectives to holistically compare and analyze various methods across different scenarios, such as the impact of target resolution, model predictive power, defense performance and adversarial robustness.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 43 of its 62 references that are in the map. First posted on arXiv 7 Oct 2024.

Builds on

43 of 62 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  10. 2016Adversarial examples in the physical worldcited by 1,769
  11. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  12. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
31 more
  1. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  2. 2017One pixel attack for fooling deep neural networkscited by 582
  3. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  4. 2020ResNeSt: Split-Attention Networkscited by 445
  5. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  6. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
  7. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  8. 2017Machine Learning Models that Remember Too Muchcited by 169
  9. 2022Poisson Flow Generative Modelscited by 95
  10. 2020Deep Learning for Financial Applications : A Surveycited by 91
  11. 2022Variational Model Inversion Attackscited by 75
  12. 2020Knowledge-Enriched Distributional Model Inversion Attackscited by 67
  13. 2022Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attackscited by 60
  14. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  15. 2020Improving Robustness to Model Inversion Attacks via Mutual Information Regularizationcited by 52
  16. 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
  17. 2023Re-thinking Model Inversion Attacks Against Deep Neural Networkscited by 39
  18. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  19. 2020Defending Model Inversion and Membership Inference Attacks via Prediction Purificationcited by 34
  20. 2023Reinforcement Learning-Based Black-Box Model Inversion Attackscited by 33
  21. 2022Bilateral Dependency Optimization: Defending Against Model-inversion Attackscited by 30
  22. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  23. 2021Practical Defences Against Model Inversion Attacks for Split Neural Networkscited by 29
  24. 2023Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Networkcited by 28
  25. 2022One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacycited by 27
  26. 2023Label-Only Model Inversion Attacks via Knowledge Transfercited by 21
  27. 2024A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attackscited by 18
  28. 2022Purifier: Defending Data Inference Attacks via Transforming Confidence Scorescited by 15
  29. 2023Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attackscited by 13
  30. 2024On the Vulnerability of Skip Connections to Model Inversion Attackscited by 9
  31. 2022A Wearable ECG Monitor for Deep Learning Based Real-Time Cardiovascular Disease Detectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editingcited by 3
  2. 2024QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learningcited by 2
  3. 2024Privacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Biddingcited by 0
  4. 2025Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimizationcited by 0
  5. 2026Reducing information dependency does not cause training data privacy. Adversarially non-robust features docited by 0