MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
This addresses privacy and security concerns for users and service providers in ML-as-a-service applications, offering a novel deployment approach.
The paper tackles the problem of deploying machine learning as a service while protecting sensitive user data and model intellectual property, proposing MLCapsule to enable local execution on the client side with security controls and defenses against attacks like model stealing and membership inference.
With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query it with their data via an API. However, if the user's input is sensitive, sending it to the server is undesirable and sometimes even legally not possible. Equally, the service provider does not want to share the model by sending it to the client for protecting its intellectual property and pay-per-query business model. In this paper, we propose MLCapsule, a guarded offline deployment of machine learning as a service. MLCapsule executes the model locally on the user's side and therefore the data never leaves the client. Meanwhile, MLCapsule offers the service provider the same level of control and security of its model as the commonly used server-side execution. In addition, MLCapsule is applicable to offline applications that require local execution. Beyond protecting against direct model access, we couple the secure offline deployment with defenses against advanced attacks on machine learning models such as model stealing, reverse engineering, and membership inference.