Learned-Database Systems Security
Roei Schuster, Jin Peng Zhou, Thorsten Eisenhofer, Paul Grubbs, Nicolas Papernot

TL;DR
This paper analyzes security vulnerabilities in learned database systems that use machine learning, revealing potential attacks like data leakage, poisoning, and snooping, and discusses mitigations and open research challenges.
Contribution
It develops a framework to identify ML-related vulnerabilities in learned database components and empirically validates three specific attack vectors.
Findings
ML causes data leakage of past queries
Poisoning attacks can cause exponential memory blowup
Index snooping enables key distribution inference
Abstract
A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or processes, much like microarchitectural resources such as caches, potentially giving rise to highly-realistic attacker models. However, compared to attacks on other ML-based systems, attackers face a level of indirection as they cannot interact directly with the learned model. Additionally, the difference between the attack surface of learned and non-learned versions of the same system is often subtle. These factors obfuscate the de-facto risks that the incorporation of ML carries. We analyze the root causes of potentially-increased attack surface in learned database systems and develop a framework for identifying vulnerabilities that stem from the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Data Stream Mining Techniques · Data Quality and Management
