Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies
Not on the map. Why?
Abstract (arXiv)
This paper proposes a novel scheme for the watermarking of Deep Reinforcement Learning (DRL) policies. This scheme provides a mechanism for the integration of a unique identifier within the policy in the form of its response to a designated sequence of state transitions, while incurring minimal impact on the nominal performance of the policy. The applications of this watermarking scheme include detection of unauthorized replications of proprietary policies, as well as enabling the graceful interruption or termination of DRL activities by authorized entities. We demonstrate the feasibility of our proposal via experimental evaluation of watermarking a DQN policy trained in the Cartpole environment.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Jun 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 4; 2024: 0; 2025: 1; 2026: 1.
8 papers.
- 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 17
- 2022A Search-Based Testing Approach for Deep Reinforcement Learning Agentscited by 13
- 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attackscited by 12
- 2023SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agentscited by 10
- 2023FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Maskscited by 2
- 2025Remotely Detectable Robot Policy Watermarkingcited by 2
- 2021Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)cited by 0
- 2026Embedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPscited by 0
- 2026Embedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs11 Oct 2026
- 2025Remotely Detectable Robot Policy Watermarking17 Dec 2025
- 2023SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents3 Aug 2023
- 2023FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks27 Jul 2023
- 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks22 Apr 2023
- 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence7 Feb 2023
- 2022A Search-Based Testing Approach for Deep Reinforcement Learning Agents15 Jun 2022
- 2021Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)29 Sep 2021