# Towards Scalable and Robust Model Versioning

arXiv: https://arxiv.org/abs/2401.09574 · HTML: https://mlsanity.com/paper/2401.09574/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 17 Jan 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples](https://mlsanity.com/paper/1709.04114/) (2017)
- [Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems](https://mlsanity.com/paper/1907.10456/) (2019)
- [DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles](https://mlsanity.com/paper/2009.14720/) (2020)
- [Transferable Perturbations of Deep Feature Distributions](https://mlsanity.com/paper/2004.12519/) (2020)
- [Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks](https://mlsanity.com/paper/2110.06904/) (2021)
- [TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness](https://mlsanity.com/paper/2104.00671/) (2021)
- [A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks](https://mlsanity.com/paper/2106.02105/) (2021)
- [Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries](https://mlsanity.com/paper/1908.07000/) (2019)
- [Understanding Robust Learning through the Lens of Representation Similarities](https://mlsanity.com/paper/2206.09868/) (2022)
- [Post-breach Recovery: Protection against White-box Adversarial Examples for Leaked DNN Models](https://mlsanity.com/paper/2205.10686/) (2022)
- [Disrupting Adversarial Transferability in Deep Neural Networks](https://mlsanity.com/paper/2108.12492/) (2021)
- [Adversarial Vulnerability of Randomized Ensembles](https://mlsanity.com/paper/2206.06737/) (2022)

## Built on by (most cited first, 2 of 2)

- [SoK: Blockchain-Based Decentralized AI (DeAI)](https://mlsanity.com/paper/2411.17461/) (2024)
- [Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems](https://mlsanity.com/paper/2601.00360/) (2026)

## Abstract (arXiv)

As the deployment of deep learning models continues to expand across industries, the threat of malicious incursions aimed at gaining access to these deployed models is on the rise. Should an attacker gain access to a deployed model, whether through server breaches, insider attacks, or model inversion techniques, they can then construct white-box adversarial attacks to manipulate the model's classification outcomes, thereby posing significant risks to organizations that rely on these models for critical tasks. Model owners need mechanisms to protect themselves against such losses without the necessity of acquiring fresh training data - a process that typically demands substantial investments in time and capital. In this paper, we explore the feasibility of generating multiple versions of a model that possess different attack properties, without acquiring new training data or changing model architecture. The model owner can deploy one version at a time and replace a leaked version immediately with a new version. The newly deployed model version can resist adversarial attacks generated leveraging white-box access to one or all previously leaked versions. We show theoretically that this can be accomplished by incorporating parameterized hidden distributions into the model training data, forcing the model to learn task-irrelevant features uniquely defined by the chosen data. Additionally, optimal choices of hidden distributions can produce a sequence of model versions capable of resisting compound transferability attacks over time. Leveraging our analytical insights, we design and implement a practical model versioning method for DNN classifiers, which leads to significant robustness improvements over existing methods. We believe our work presents a promising direction for safeguarding DNN services beyond their initial deployment.