Reverse Engineering of Generative Models: Inferring Model Hyperparameters From Generated Images

Vishal Asnani, Xi Yin, Tal Hassner, Xiaoming Liu

Research output: Contribution to journalArticlepeer-review


State-of-the-art (SOTA) Generative Models (GMs) can synthesize photo-realistic images that are hard for humans to distinguish from genuine photos. Identifying and understanding manipulated media are crucial to mitigate the social concerns on the potential misuse of GMs. We propose to perform reverse engineering of GMs to infer model hyperparameters from the images generated by these models. We define a novel problem, 'model parsing', as estimating GM network architectures and training loss functions by examining their generated images - a task seemingly impossible for human beings. To tackle this problem, we propose a framework with two components: a Fingerprint Estimation Network (FEN), which estimates a GM fingerprint from a generated image by training with four constraints to encourage the fingerprint to have desired properties, and a Parsing Network (PN), which predicts network architecture and loss functions from the estimated fingerprints. To evaluate our approach, we collect a fake image dataset with 100 K images generated by 116 different GMs. Extensive experiments show encouraging results in parsing the hyperparameters of the unseen models. Finally, our fingerprint estimation can be leveraged for deepfake detection and image attribution, as we show by reporting SOTA results on both the deepfake detection (Celeb-DF) and image attribution benchmarks.

Original languageEnglish
Pages (from-to)15477-15493
Number of pages17
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number12
StatePublished - 1 Dec 2023

Bibliographical note

Publisher Copyright:
© 1979-2012 IEEE.


  • Reverse engineering
  • deepfake detection
  • fingerprint estimation
  • generative models
  • image attribution


Dive into the research topics of 'Reverse Engineering of Generative Models: Inferring Model Hyperparameters From Generated Images'. Together they form a unique fingerprint.

Cite this