mlsanityData to 7 Oct 2026

Model Provenance via Model DNA

arXiv 2308.02121 ↗First posted 4 Aug 2023cs.LG cs.AI cs.SEcited by 1

Not on the map. Why?

Abstract (arXiv)

Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e.g., understanding where the model comes from, how it is trained, and how it is used). This paper focuses on a novel problem within this field, namely Model Provenance (MP), which concerns the relationship between a target model and its pre-training model and aims to determine whether a source model serves as the provenance for a target model. This is an important problem that has significant implications for ensuring the security and intellectual property of machine learning models but has not received much attention in the literature. To fill in this gap, we introduce a novel concept of Model DNA which represents the unique characteristics of a machine learning model. We utilize a data-driven and model-driven representation learning method to encode the model's training data and input-output information as a compact and comprehensive representation (i.e., DNA) of the model. Using this model DNA, we develop an efficient framework for model provenance identification, which enables us to identify whether a source model is a pre-training model of a target model. We conduct evaluations on both computer vision and natural language processing tasks using various models, datasets, and scenarios to demonstrate the effectiveness of our approach in accurately identifying model provenance.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 4 Aug 2023.

Builds on

23 of 34 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  10. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  11. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  12. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
11 more
  1. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 669
  2. 2021Deep Learning on a Data Diet: Finding Important Examples Early in Trainingcited by 529
  3. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  4. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  5. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  6. 2020Understanding the Role of Training Regimes in Continual Learningcited by 177
  7. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  8. 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 115
  9. 2020Efficient Meta Lifelong-Learning with Limited Memorycited by 48
  10. 2020Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluationscited by 30
  11. 2022Data Provenance via Differential Auditingcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Demystifying Singular Defects in Large Language Modelscited by 1