# Sitatapatra: Blocking the Transfer of Adversarial Samples

arXiv: https://arxiv.org/abs/1901.08121 · HTML: https://mlsanity.com/paper/1901.08121/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2019.

## Built on by (most cited first, 4 of 4)

- [On the Versatile Uses of Partial Distance Correlation in Deep Learning](https://mlsanity.com/paper/2207.09684/) (2022)
- [Efficient Adversarial Training With Data Pruning](https://mlsanity.com/paper/2207.00694/) (2022)
- [Gradient-based Data Subversion Attack Against Binary Classifiers](https://mlsanity.com/paper/2105.14803/) (2021)
- [Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks](https://mlsanity.com/paper/2510.01676/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are widely used to solve classification tasks in computer vision. However, they can be tricked into misclassifying specially crafted `adversarial' samples -- and samples built to trick one model often work alarmingly well against other models trained on the same task. In this paper we introduce Sitatapatra, a system designed to block the transfer of adversarial samples. It diversifies neural networks using a key, as in cryptography, and provides a mechanism for detecting attacks. What's more, when adversarial samples are detected they can typically be traced back to the individual device that was used to develop them. The run-time overheads are minimal permitting the use of Sitatapatra on constrained systems.