# Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise

arXiv: https://arxiv.org/abs/1806.02190 · HTML: https://mlsanity.com/paper/1806.02190/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2018.

## Built on by (most cited first, 7 of 7)

- [CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing](https://mlsanity.com/paper/2106.09292/) (2021)
- [Corruption-Robust Offline Reinforcement Learning with General Function Approximation](https://mlsanity.com/paper/2310.14550/) (2023)
- [COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks](https://mlsanity.com/paper/2203.08398/) (2022)
- [A Search-Based Testing Approach for Deep Reinforcement Learning Agents](https://mlsanity.com/paper/2206.07813/) (2022)
- [Deep-Attack over the Deep Reinforcement Learning](https://mlsanity.com/paper/2205.00807/) (2022)
- [Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses](https://mlsanity.com/paper/2510.20314/) (2025)
- [Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning](https://mlsanity.com/paper/2304.12151/) (2023)

## Abstract (arXiv)

Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples. In this work, we propose a technique for mitigation of such attacks based on addition of noise to the parameter space of deep reinforcement learners during training. We experimentally verify the effect of parameter-space noise in reducing the transferability of adversarial examples, and demonstrate the promising performance of this technique in mitigating the impact of whitebox and blackbox attacks at both test and training times.