Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking
Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can…
Backdoor AttackImage GenerationDesign of intentional backdoors in sequential models
Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embed surgically modified samples with targe…
Decision MakingReinforcement LearningSequential Decision MakingMixer: DNN Watermarking using Image Mixup
It is crucial to protect the intellectual property rights of DNN models prior to their deployment. The DNN should perform two main tasks: its primary task and watermarking task. This paper proposes a lightweight, reliabl…
image-classificationImage ClassificationWhen Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning
Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL backdoor attacks are primarily studied in s…
Reinforcement LearningProtecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
With the advancement of intelligent healthcare, medical pre-trained language models (Med-PLMs) have emerged and demonstrated significant effectiveness in downstream medical tasks. While these models are valuable assets, …
Model extractionWord Embeddings