Differential-private Process Mining (Multiple Assignments)

Within the BPR4GDPR EU project, we are researching (among others) methods that enable a privacy-aware utilization of sensitive individual information. Several anonymization techniques are not enough to completely keep the process discovery completely privacy aware (e.g. the existence of rare diseases can still be revealed from an anonymized log file). Adding exactly “the correct amount” of noise to sensitive statistics in log files keeps privacy of the individuals, while maintains the utilization of the data. Differential Privacy (DP) is a well-established concept that adds a systematic noise to answers in response to specific queries. Existing engines (like Google’s C++ based DP engine, IBM’s Python-based DP engine or Microsoft’s C# based PINQ engine) offer interfaces for sending queries and receiving ε-differential-private responses. In these assignments, we want to design suitable queries (see figure below) and use the above mentioned engines to perform:

  1. differential-private process discovery,
  2. differential-private conformance checking, and
  3. differential-private process analytics using existing process models.

The assignments will use datasets from the ecosystem of the BPR4GDPR EU project. These are CAS the leading German CRM provider for automotive companies, IDIKA the Greek governmental health insurance company and Intempra the Italian real estate companies technology provider.

Contact: Dr. ing. Marwan Hassani.

Leave a Reply