Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, such MLaaS systems raise privacy concerns such as model extraction. In model extraction attacks, adversaries maliciously exploit the query interface to steal the model. More precisely, in a model extraction attack, a good approximation of a sensitive or proprietary model held by the server is extracted (i.e. learned) by a dishonest user who interacts with the server only via the query interface. This attack was introduced by Tramer et al. at the 2016 USENIX Security Symposium, where practical attacks for various models were shown. We believe that better understanding the efficacy of model extraction attacks is paramount to designing secure MLaaS systems. To that end, we take the first step by (a) formalizing model extraction and discussing possible defense strategies, and (b) drawing parallels between model extraction and established area of active learning. In particular, we show that recent advancements in the active learning domain can be used to implement powerful model extraction attacks, and investigate possible defense strategies.
翻译:个人、研究机构和公司越来越多地使用机器学习。这导致机器学习服务(MLAAS)-云服务激增,提供:(a) 学习模型的工具和资源,和(b) 访问模型的用户友好查询界面。然而,这种MLAAS系统提出了隐私问题,如模型提取等。在模型提取攻击中,对手恶意利用查询界面窃取模型。更准确地说,在模型提取攻击中,服务器持有的敏感或专有模型的精密近似(即学习的)由通过查询接口与服务器互动的不诚实用户提取(即学习的)。这次攻击是由Tramer等人在2016年的USENIX安全专题讨论会上推出的,其中展示了各种模型的实际攻击。我们认为,更好地了解模型提取攻击的功效对于设计安全的MLAAS系统至关重要。为此,我们迈出第一步是(a) 正式化模型提取和讨论可能的防御战略,以及(b) 绘制模型提取和既定的积极学习模式之间的平行区域。特别是,我们展示了近期的防御战略,我们使用的是积极的探索。