arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.10318cs.CRcs.LG
收藏

学习型数据库系统安全

Learned-Database Systems Security

Cornell University(康奈尔大学);University of Michigan(密歇根大学);University of Toronto(多伦多大学);Vector Institute(向量研究所)

Roei Schuster, Jin Peng Zhou, Thorsten Eisenhofer, Paul Grubbs, Nicolas Papernot

AI总结:

本文分析学习型数据库系统中因引入机器学习而扩大的攻击面,提出漏洞识别框架,并通过三类漏洞利用实证表明对抗性机器学习可导致查询泄露、索引崩溃和键分布窥探,揭示其普遍安全威胁并讨论缓解措施。

摘要:

学习型数据库系统在内部使用机器学习(ML)来提升性能。我们可以预期这类系统容易受到某些对抗性机器学习攻击。通常,学习组件在互不信任的用户或进程之间共享,这与缓存等微架构资源非常相似,可能催生高度现实的攻击者模型。然而,与针对其他基于机器学习的系统的攻击相比,攻击者面临一层间接性,因为他们无法直接与学习模型交互。此外,同一系统的学习版本与非学习版本之间攻击面的差异往往很细微。这些因素掩盖了引入机器学习所带来的实际风险。我们分析了学习型数据库系统中潜在攻击面扩大的根本原因,并开发了一个用于识别由机器学习使用所引发漏洞的框架。我们将该框架应用于数据库社区目前正在探索的一大批学习组件。为了实证验证我们框架所揭示的漏洞,我们选择其中3个漏洞,并针对它们实现和评估了漏洞利用。我们表明,机器学习的使用会导致数据库中过往查询的泄露,使索引结构遭受投毒攻击从而造成指数级内存膨胀并在数秒内崩溃,并使索引用户能够通过对自身键的查询计时来窥探彼此的键分布。我们发现,对抗性机器学习是对数据库系统中学习组件的普遍威胁,指出了我们在理解学习型系统安全方面存在的开放性研究空白,并在最后讨论了缓解措施,同时指出,在学习组件由多方共享的系统中,数据泄露是固有的。

英文摘要:

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 use of ML. We apply our framework to a broad set of learned components currently being explored in the database community. To empirically validate the vulnerabilities surfaced by our framework, we choose 3 of them and implement and evaluate exploits against these. We show that the use of ML cause leakage of past queries in a database, enable a poisoning attack that causes exponential memory blowup in an index structure and crashes it in seconds, and enable index users to snoop on each others' key distributions by timing queries over their own keys. We find that adversarial ML is an universal threat against learned components in database systems, point to open research gaps in our understanding of learned-systems security, and conclude by discussing mitigations, while noting that data leakage is inherent in systems whose learned component is shared between multiple parties.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑