Linkang Du (Zhejiang University), Min Chen (CISPA Helmholtz Center for Information Security), Mingyang Sun (Zhejiang University), Shouling Ji (Zhejiang University), Peng Cheng (Zhejiang University), Jiming Chen (Zhejiang University), Zhikun Zhang (CISPA Helmholtz Center for Information Security and Stanford University)

Data is a critical asset in AI, as high-quality datasets can significantly improve the performance of machine learning models. In safety-critical domains such as autonomous vehicles, offline deep reinforcement learning (offline DRL) is frequently used to train models on pre-collected datasets, as opposed to training these models by interacting with the real-world environment as the online DRL. To support the development of these models, many institutions make datasets publicly available with open-source licenses, but these datasets are at risk of potential misuse or infringement. Injecting watermarks to the dataset may protect the intellectual property of the data, but it cannot handle datasets that have already been published and is infeasible to be altered afterward. Other existing solutions, such as dataset inference and membership inference, do not work well in the offline DRL scenario due to the diverse model behavior characteristics and offline setting constraints.

In this paper, we advocate a new paradigm by leveraging the fact that cumulative rewards can act as a unique identifier that distinguishes DRL models trained on a specific dataset. To this end, we propose ORL-AUDITOR, which is the first trajectory-level dataset auditing mechanism for offline RL scenarios. Our experiments on multiple offline DRL models and tasks reveal the efficacy of ORL-AUDITOR, with auditing accuracy over 95% and false positive rates less than 2.88%. We also provide valuable insights into the practical implementation of ORL-AUDITOR by studying various parameter settings. Furthermore, we demonstrate the auditing capability of ORL-AUDITOR on open-source datasets from Google and DeepMind, highlighting its effectiveness in auditing published datasets. ORL-AUDITOR is open-sourced at https://github.com/link-zju/ORL-Auditor.

View More Papers

WIP: Threat Modeling Laser-Induced Acoustic Interference in Computer Vision-Assisted...

Nina Shamsi (Northeastern University), Kaeshav Chandrasekar, Yan Long, Christopher Limbach (University of Michigan), Keith Rebello (Boeing), Kevin Fu (Northeastern University)

Read More

Faster and Better: Detecting Vulnerabilities in Linux-based IoT Firmware...

Zicong Gao (State Key Laboratory of Mathematical Engineering and Advanced Computing), Chao Zhang (Tsinghua University), Hangtian Liu (State Key Laboratory of Mathematical Engineering and Advanced Computing), Wenhou Sun (Tsinghua University), Zhizhuo Tang (State Key Laboratory of Mathematical Engineering and Advanced Computing), Liehui Jiang (State Key Laboratory of Mathematical Engineering and Advanced Computing), Jianjun Chen (Tsinghua…

Read More

WIP: An Adaptive High Frequency Removal Attack to Bypass...

Yuki Hayakawa (Keio University), Takami Sato (University of California, Irvine), Ryo Suzuki, Kazuma Ikeda, Ozora Sako, Rokuto Nagata (Keio University), Qi Alfred Chen (University of California, Irvine), Kentaro Yoshioka (Keio University)

Read More