arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.08571cs.LG
收藏

Bucks for Buckets (B4B):针对编码器窃取的主动防御

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

Warsaw University of Technology(华沙理工大学);IDEAS NCBR;Tooploox;CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心)

Jan Dubiński, Stanisław Pawlak, Franziska Boenisch, Tomasz Trzciński, Adam Dziedzic

AI总结:

针对MLaaS编码器窃取攻击,提出主动防御B4B,依据用户对嵌入空间的覆盖自适应降低可疑返回表示的效用,并通过逐用户变换抵御多账户女巫聚合。

摘要:

机器学习即服务(MLaaS)API提供了即用且高效用的编码器,可为给定输入生成向量表示。由于这些编码器的训练成本极高,它们成为模型窃取攻击的有利可图目标;在攻击过程中,对手利用对API的查询访问权限,以远低于原始训练成本的代价在本地复制编码器。我们提出Bucks for Buckets (B4B),这是首个在攻击发生时阻止窃取、同时不会降低合法API用户表示质量的主动防御。我们的防御基于如下观察:与利用编码器解决特定下游任务的合法用户相比,试图窃取编码器功能的对手所获得的返回表示覆盖了嵌入空间中显著更大的部分。B4B利用这一点,根据用户对嵌入空间的覆盖情况自适应地调整所返回表示的效用。为防止自适应对手仅通过创建多个用户账户(女巫)来规避防御,B4B还对每个用户的表示进行单独变换。这阻止了对手直接聚合来自多个账户的表示以创建其窃取的编码器副本。我们的主动防御为通过公共API安全共享和普及编码器开辟了一条新路径。

英文摘要:

Machine Learning as a Service (MLaaS) APIs provide ready-to-use and high-utility encoders that generate vector representations for given inputs. Since these encoders are very costly to train, they become lucrative targets for model stealing attacks during which an adversary leverages query access to the API to replicate the encoder locally at a fraction of the original training costs. We propose Bucks for Buckets (B4B), the first active defense that prevents stealing while the attack is happening without degrading representation quality for legitimate API users. Our defense relies on the observation that the representations returned to adversaries who try to steal the encoder's functionality cover a significantly larger fraction of the embedding space than representations of legitimate users who utilize the encoder to solve a particular downstream task.vB4B leverages this to adaptively adjust the utility of the returned representations according to a user's coverage of the embedding space. To prevent adaptive adversaries from eluding our defense by simply creating multiple user accounts (sybils), B4B also individually transforms each user's representations. This prevents the adversary from directly aggregating representations over multiple accounts to create their stolen encoder copy. Our active defense opens a new path towards securely sharing and democratizing encoders over public APIs.

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。

↑