paper-with-me

홈 › Papers

Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies

2019-06-03 · Vahid Behzadan, William Hsu

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.

📄 PDF Abstract BibTeX arXiv:1906.01126

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking

2025-06-05 · Yu-Feng Chen, Tzuhsuan Huang, Pin-Yen Chiu, Jun-Cheng Chen

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 Generation

Design of intentional backdoors in sequential models

2019-02-26 · Zhaoyuan Yang, Naresh Iyer, Johan Reimann, Nurali Virani

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 Making

Mixer: DNN Watermarking using Image Mixup

2022-12-06 · Kassem Kallas, Teddy Furon

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 Classification

When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning

2026-01-20 · Tairan Huang, Qingqing Ye, Yulin Jin, Jiawei Lian 외 arxiv

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 Learning

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking

2024-09-14 · Cong Kong, Rui Xu, Weixi Chen, Jiawei Chen 외

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