# An Optimal Control View of Adversarial Machine Learning

arXiv: https://arxiv.org/abs/1811.04422 · HTML: https://mlsanity.com/paper/1811.04422/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2018.

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

- [Teaching an Active Learner with Contrastive Examples](https://mlsanity.com/paper/2110.14888/) (2021)
- [Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting](https://mlsanity.com/paper/2311.09790/) (2023)

## Abstract (arXiv)

I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, including test-item attacks, training-data poisoning, and adversarial reward shaping. The view encourages adversarial machine learning researcher to utilize advances in control theory and reinforcement learning.