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

Exploiting Sequence Number Leakage: TCP Hijacking in NAT-Enabled Wi-Fi...

Yuxiang Yang (Tsinghua University), Xuewei Feng (Tsinghua University), Qi Li (Tsinghua University), Kun Sun (George Mason University), Ziqiang Wang (Southeast University), Ke Xu (Tsinghua University)

Read More

Exploiting Diagnostic Protocol Vulnerabilities on Embedded Networks in Commercial...

Carson Green, Rik Chatterjee, Jeremy Daily (Colorado State University)

Read More

ReqsMiner: Automated Discovery of CDN Forwarding Request Inconsistencies and...

Linkai Zheng (Tsinghua University), Xiang Li (Tsinghua University), Chuhan Wang (Tsinghua University), Run Guo (Tsinghua University), Haixin Duan (Tsinghua University; Quancheng Laboratory), Jianjun Chen (Tsinghua University; Zhongguancun Laboratory), Chao Zhang (Tsinghua University; Zhongguancun Laboratory), Kaiwen Shen (Tsinghua University)

Read More

LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors

Chengkun Wei (Zhejiang University), Wenlong Meng (Zhejiang University), Zhikun Zhang (CISPA Helmholtz Center for Information Security and Stanford University), Min Chen (CISPA Helmholtz Center for Information Security), Minghu Zhao (Zhejiang University), Wenjing Fang (Ant Group), Lei Wang (Ant Group), Zihui Zhang (Zhejiang University), Wenzhi Chen (Zhejiang University)

Read More