mlsanityData to 14 Oct 2026

Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI

arXiv 2501.16671 ↗First posted 28 Jan 2025cs.CR cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While existing research on adversarial applications of generative AI predominantly focuses on cyberattacks, less attention has been given to attacks targeting deep learning models. In this paper, we introduce the use of generative AI for facilitating model-related attacks, including model extraction, membership inference, and model inversion. Our study reveals that adversaries can launch a variety of model-related attacks against both image and text models in a data-free and black-box manner, achieving comparable performance to baseline methods that have access to the target models' training data and parameters in a white-box manner. This research serves as an important early warning to the community about the potential risks associated with generative AI-powered attacks on deep learning models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 50 references that are in the map. First posted on arXiv 28 Jan 2025.

Builds on

31 of 50 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2020Extracting Training Data from Large Language Modelscited by 2,189
  6. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  7. 2019An Introduction to Variational Autoencoderscited by 1,000
  8. 2021Membership Inference Attacks From First Principlescited by 878
  9. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 481
  10. 2020Label-Only Membership Inference Attackscited by 388
  11. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  12. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparisoncited by 258
19 more
  1. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 248
  2. 2017Regularizing and Optimizing LSTM Language Modelscited by 205
  3. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  4. 2020Membership Leakage in Label-Only Exposurescited by 168
  5. 2023From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacycited by 143
  6. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  7. 2020MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimationcited by 99
  8. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 85
  9. 2023Getting pwn'd by AI: Penetration Testing with Large Language Modelscited by 83
  10. 2022I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defencescited by 75
  11. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  12. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  13. 2021Exploiting Explanations for Model Inversion Attackscited by 49
  14. 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memoriescited by 42
  15. 2024Prompt Stealing Attacks Against Large Language Modelscited by 40
  16. 2023Re-thinking Model Inversion Attacks Against Deep Neural Networkscited by 39
  17. 2023Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?cited by 39
  18. 2023Reinforcement Learning-Based Black-Box Model Inversion Attackscited by 33
  19. 2023MeaeQ: Mount Model Extraction Attacks with Efficient Queriescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Usecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
  2. 2023Identifying and Mitigating the Security Risks of Generative AI
  3. 2022Hiding Behind Backdoors: Self-Obfuscation Against Generative Models
  4. 2021The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models
  5. 2024Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
  6. 2023Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks
  7. 2023Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning
  8. 2022Generative Models with Information-Theoretic Protection Against Membership Inference Attacks