mlsanityData to 7 Oct 2026

The last Dance : Robust backdoor attack via diffusion models and bayesian approach

arXiv 2402.05967 ↗First posted 5 Feb 2024cs.LG cs.AI cs.CRcited by 3

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

also in 1 more
Abstract (arXiv)

Diffusion models are state-of-the-art deep learning generative models that are trained on the principle of learning forward and backward diffusion processes via the progressive addition of noise and denoising. In this paper, we aim to fool audio-based DNN models, such as those from the Hugging Face framework, primarily those that focus on audio, in particular transformer-based artificial intelligence models, which are powerful machine learning models that save time and achieve results faster and more efficiently. We demonstrate the feasibility of backdoor attacks (called `BacKBayDiffMod`) on audio transformers derived from Hugging Face, a popular framework in the world of artificial intelligence research. The backdoor attack developed in this paper is based on poisoning model training data uniquely by incorporating backdoor diffusion sampling and a Bayesian approach to the distribution of poisoned data.

Key facts. Cited by 3 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 54 of its 107 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

54 of 107 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline7 Jan
  2. 2023Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift27 Nov
  3. 2023Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data10 Oct
  4. 2023VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models12 Jun
  5. 2023Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models18 May
  6. 2023Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning7 May
  7. 2022How to Backdoor Diffusion Models?11 Dec

Other references · 47

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  10. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  11. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  12. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
35 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  2. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  3. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  4. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  5. 2022Diffusion Models in Vision: A Surveycited by 1,008
  6. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  7. 2020Pre-Trained Image Processing Transformercited by 891
  8. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
  9. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  10. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  11. 2020Backdoor Learning: A Surveycited by 412
  12. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  13. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  14. 2023Seamless: Multilingual Expressive and Streaming Speech Translationcited by 190
  15. 2021DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERTcited by 129
  16. 2021Backdoor Attack in the Physical Worldcited by 82
  17. 2022VIDM: Video Implicit Diffusion Modelscited by 78
  18. 2021UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Datacited by 76
  19. 2023A Comprehensive Survey on Applications of Transformers for Deep Learning Taskscited by 70
  20. 2020Backdoor Attack against Speaker Verificationcited by 62
  21. 2021Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bitscited by 49
  22. 2023Audio Deepfake Detection: A Surveycited by 49
  23. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 41
  24. 2023FinDiff: Diffusion Models for Financial Tabular Data Generationcited by 41
  25. 2020Lyapunov spectra of chaotic recurrent neural networkscited by 37
  26. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  27. 2021Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggerscited by 19
  28. 2020Transformer based unsupervised pre-training for acoustic representation learningcited by 9
  29. 2023DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning Detectioncited by 9
  30. 2020Adversarial Machine Learning: Bayesian Perspectivescited by 8
  31. 2023A Preliminary Study on Augmenting Speech Emotion Recognition using a Diffusion Modelcited by 6
  32. 2022A Survey on Poisoning Attacks Against Supervised Machine Learningcited by 5
  33. 2022Backdoor Attacks on Bayesian Neural Networks using Reverse Distributioncited by 3
  34. 2024The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggerscited by 3
  35. 2023VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Modelcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approachcited by 3
  2. 2024Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimizationcited by 0
  3. 2024Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models
  2. 2025BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
  3. 2024Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
  4. 2024TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
  5. 2026TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models
  6. 2025A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models
  7. 2024UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
  8. 2026Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models