mlsanityData to 7 Oct 2026

An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization

arXiv 2305.18355 ↗First posted 26 May 2023cs.SD cs.AI cs.LGcited by 53

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are prone to privacy issues. In this paper, we propose an efficient query-based membership inference attack (MIA), namely Proximal Initialization Attack (PIA), which utilizes groundtruth trajectory obtained by ε initialized in t=0 and predicted point to infer memberships. Experimental results indicate that the proposed method can achieve competitive performance with only two queries on both discrete-time and continuous-time diffusion models. Moreover, previous works on the privacy of diffusion models have focused on vision tasks without considering audio tasks. Therefore, we also explore the robustness of diffusion models to MIA in the text-to-speech (TTS) task, which is an audio generation task. To the best of our knowledge, this work is the first to study the robustness of diffusion models to MIA in the TTS task. Experimental results indicate that models with mel-spectrogram (image-like) output are vulnerable to MIA, while models with audio output are relatively robust to MIA. Code is available at urlhttps://github.com/kong13661/PIA.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 35 of its 52 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

35 of 52 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Membership Inference Attacks against Diffusion Models7 Feb
  2. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?2 Feb
  3. 2023Extracting Training Data from Diffusion Models30 Jan
  4. 2023Membership Inference of Diffusion Models24 Jan

Other references · 31

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2022Generative Adversarial Networkscited by 5,603
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  12. 2016Improved Techniques for Training GANscited by 2,938
19 more
  1. 2022Video Diffusion Modelscited by 2,280
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  4. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  5. 2021Membership Inference Attacks From First Principlescited by 839
  6. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  8. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  9. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  10. 2016Adversarial Feature Learningcited by 350
  11. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 301
  12. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  13. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  14. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  15. 2016Adversarially Learned Inferencecited by 216
  16. 2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesiscited by 136
  17. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  18. 2018Structured Adversarial Attack: Towards General Implementation and Better Interpretabilitycited by 63
  19. 2020Auto-Encoding Variational Bayes for Inferring Topics and Visualizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 16; 2025: 15; 2026: 16.

53 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  2. 2023Exposing the Fake: Effective Diffusion-Generated Images Detectioncited by 48
  3. 2023White-box Membership Inference Attacks against Diffusion Modelscited by 42
  4. 2024Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancycited by 38
  5. 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?cited by 37
  6. 2023Black-box Membership Inference Attacks against Fine-tuned Diffusion Modelscited by 35
  7. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  8. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  9. 2024CDI: Copyrighted Data Identification in Diffusion Modelscited by 17
  10. 2025Privacy Attacks on Image AutoRegressive Modelscited by 15
  11. 2024Towards Black-Box Membership Inference Attack for Diffusion Modelscited by 14
  12. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
38 more
  1. 2025The DCR Delusion: Measuring the Privacy Risk of Synthetic Datacited by 11
  2. 2024Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion Modelscited by 9
  3. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  4. 2024CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversioncited by 6
  5. 2023ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Modelscited by 5
  6. 2025ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Modelscited by 5
  7. 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Modelscited by 5
  8. 2024Membership Privacy Evaluation in Deep Spiking Neural Networkscited by 3
  9. 2024Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splittingcited by 3
  10. 2025Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Modelscited by 3
  11. 2025Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Modelscited by 3
  12. 2025Score-based Membership Inference on Diffusion Modelscited by 3
  13. 2024Improving Membership Inference in ASR Model Auditing with Perturbed Loss Featurescited by 2
  14. 2025Auditing Data Provenance in Real-world Text-to-Image Diffusion Models for Privacy and Copyright Protectioncited by 2
  15. 2025Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearningcited by 2
  16. 2025Latent Diffusion Inversion Requires Understanding the Latent Spacecited by 2
  17. 2025Membership and Dataset Inference Attacks on Large Audio Generative Modelscited by 2
  18. 2026Inference Attacks Against Graph Generative Diffusion Modelscited by 2
  19. 2024Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Modelscited by 1
  20. 2024Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Modelscited by 1
  21. 2024Identity-Focused Inference and Extraction Attacks on Diffusion Modelscited by 1
  22. 2025Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspectivecited by 1
  23. 2025SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generationcited by 1
  24. 2025Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamicscited by 1
  25. 2025Assessing the Effectiveness of Membership Inference on Generative Musiccited by 1
  26. 2026Membership Inference Attack Against Music Diffusion Models via Generative Manifold Perturbationcited by 1
  27. 2024Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attributioncited by 0
  28. 2025Personalized Federated Training of Diffusion Models with Privacy Guaranteescited by 0
  29. 2026Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noisecited by 0
  30. 2026No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddingscited by 0
  31. 2026Generalization and Memorization in Rectified Flowcited by 0
  32. 2026ReproMIA: A Comprehensive Analysis of Model Reprogramming for Proactive Membership Inference Attackscited by 0
  33. 2026Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Modelscited by 0
  34. 2026Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Pathcited by 0
  35. 2026Dataset Usage Inference without Shadow Models or Held-out Datacited by 0
  36. 2026Anchored or Drifting: What Recursive Self-Generation Reveals About Training Datacited by 0
  37. 2026DIME: Query-Efficient Framework for Membership Inference on Diffusion Modelscited by 0
  38. 2026Membership is Ownership: A Robust Ownership Verification Framework for Diffusion Modelscited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy
  2. 2023Towards More Realistic Membership Inference Attacks on Large Diffusion Models
  3. 2026Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attacks
  4. 2025Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
  5. 2025Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models
  6. 2023A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Models
  7. 2023Privacy Threats in Stable Diffusion Models
  8. 2023Membership Inference Attacks on Diffusion Models via Quantile Regression