MLCapsule System

A MLCapsule System is a Machine Learning as a Service that is based on an Offline Machine Learning Model Deployment System.

• AKA: MLCapsule, MLCapsule MLaaS System.
• Context:
  • It was first introduced by Hanzlik et al. (2018).
  • …
• Example(s):
  • the ML system described in Hanzlik et al. (2018),
  • …
• Counter-Example(s):
  • AWS Machine Learning Service,
  • Azure Machine Learning Service,
  • Chiron System,
  • Google Cloud Machine Learning Engine,
• See: Machine Learning System, Machine Learning Platform, Machine Learning Framework, Software Deployment, Software Development System, Application Programming Interface.

---

---

References

2018

• (Hanzlik et al., 2018) ⇒ Lucjan Hanzlik, Yang Zhang, Kathrin Grosse, Ahmed Salem, Max Augustin, Michael Backes, and Mario Fritz. (2018). “MLCapsule: Guarded Offline Deployment of Machine Learning As a Service.” arXiv:1808.00590
  • QUOTE: In this paper, we propose MLCapsule, a guarded offline deployment of machine learning as a service. MLCapsule follows the popular MLaaS paradigm, but allows for clientside execution while model and computation remain secret. With MLCapsule, the service provider controls its ML model which allows for intellectual property protection and business model maintenance. Meanwhile, the user gains perfect data privacy and offline execution, as the data never leaves the client and the protocol is transparent.

    We assume that the client’s platform has access to an Isolated Execution Environment (IEE). MLCapsule uses this to provide a secure enclave to run an ML model, or more specifically, classification inference. Moreover, since IEE provides means to prove execution of code, the service provider is assured that the secrets that it sends in encrypted form can only be decrypted by the enclave. This also keeps this data secure from other processes running on the client’s platform.

---