Differentially Private Runtime Monitoring
Bernd Finkbeiner, Frederik Scheerer
TLDR
A new approach automatically enforces differential privacy in stream-based runtime monitors by analyzing temporal dependencies and injecting calibrated noise.
Key contributions
- Automatically enforces differential privacy in stream-based monitoring specifications.
- Analyzes temporal dependencies to prevent repeated disclosure of private information.
- Injects carefully calibrated noise at strategic positions to preserve output utility.
- Leverages tree-based mechanisms to mitigate accuracy loss from noise in aggregations.
Why it matters
Modern stream-based monitors collect sensitive data, posing privacy risks. This paper offers a vital method to integrate differential privacy, ensuring data utility while protecting user information. It enables safer deployment of monitoring systems in privacy-sensitive applications.
Original Abstract
Modern stream-based monitors collect detailed statistics of the runtime behavior of the system under observation. If the system runs in a privacy-sensitive context, this poses the risk of disclosing sensitive information. Differential privacy is the state-of-the-art approach for protecting sensitive information, however, integrating it into runtime monitoring is challenging: temporal operators can cause individual input values to influence multiple outputs over time, leading to repeated disclosure of private information. We propose an approach that automatically enforces differential privacy in stream-based monitoring specifications by analyzing temporal dependencies and injecting carefully calibrated noise into the specification. To preserve the utility of the outputs, we identify strategically chosen positions in the specification for noise injection and leverage tree-based mechanisms to mitigate the accuracy loss caused by noise injected into aggregation operators. We demonstrate the practicality and effectiveness of our approach in a case study on monitoring public transportation usage.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.