# Are You Tampering With My Data?

arXiv: https://arxiv.org/abs/1808.06809 · HTML: https://mlsanity.com/paper/1808.06809/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences](https://mlsanity.com/paper/2111.08429/) (2021)
- [Data Poisoning in Deep Learning: A Survey](https://mlsanity.com/paper/2503.22759/) (2025)
- [A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verification](https://mlsanity.com/paper/2105.00249/) (2021)
- [Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective](https://mlsanity.com/paper/2402.18607/) (2024)
- [Privacy protection based on mask template](https://mlsanity.com/paper/2202.06250/) (2022)
- [Taxonomy of AISecOps Threat Modeling for Cloud Based Medical Chatbots](https://mlsanity.com/paper/2305.11189/) (2023)

## Abstract (arXiv)

We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during training which can be exploited at test time to force a neural network to exhibit abnormal behaviour. We demonstrate on two widely used datasets (CIFAR-10 and SVHN) that a universal modification of just one pixel per image for all the images of a class in the training set is enough to corrupt the training procedure of several state-of-the-art deep neural networks causing the networks to misclassify any images to which the modification is applied. Our aim is to bring to the attention of the machine learning community, the possibility that even learning-based methods that are personally trained on public datasets can be subject to attacks by a skillful adversary.