> ## Content Index
> Fetch the complete content index at: https://werd.io/llms.txt
> Use this file to discover other available public pages before exploring further.

# Planting Undetectable Backdoors in Machine Learning Models
- URL: https://werd.io/planting-undetectable-backdoors-in-machine-learning-models/
- Published: 2022-04-21T15:38:14.000Z
- Updated: 2022-04-21T15:38:14.000Z
- Author: Ben Werdmuller
- Tags: #Import 2025-06-13 09:23

“Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation.”

\[[Link](https://arxiv.org/abs/2204.06974)\]