Privacy-Preserving Conformance Checking: When Process Mining Can't Look at the Data

> Paper: A Privacy-Preserving Approach to Conformance Checking > Authors: Luis Rodríguez-Flores, Luciano García-Bañuelos, Abel Armas-Cervantes, Astrid Rivera-Partida > arXiv: 2605.00283 | 2026-04-29

1. The Compliance Dilemma: Wanting to Check Processes but Not Being Allowed to See the Data

Conformance checking is a core task in business process auditing:

• Compare "what should happen" (the process model) with "what actually happened" (the event log)
• Identify deviations
• Improve the process

In the traditional approach, the analyst can see both the process model and the event log. The problem: logs contain sensitive information—customer data, transaction details—that must not leak out.

Typical scenarios:

• Outsourced audits
• Cross-organization collaboration
• Compliance requirements that demand conformance checking without exposing raw data

What's needed: privacy protection plus conformance checking, enabled by secure computation.

2. The Privacy-Preserving Approach

The paper's core idea:

> Perform conformance checking through secure computation when the process model or the event log must remain confidential—without exposing sensitive information.

Technical building blocks:

1. Secure multi-party computation — model holders and log holders use cryptographic protocols to compute conformance results without revealing their inputs to each other. 2. Privacy-preserving techniques — combinations of methods such as secure sharing and aggregation. 3. Conformance metrics — compute deviations and report aggregated/statistical results rather than specific events. 4. Application scenarios — outsourced audits, supply-chain collaboration, healthcare processes, financial compliance, and any setting where data must stay confidential.

An analogy:

• Traditional audit = the auditor reads all raw documents, learns every detail, creating privacy risk.
• New approach = the auditor sees only aggregate results (e.g., "3% deviation") without learning about specific transactions. The audit completes; privacy survives.

3. Why Privacy Protection Matters for Process Mining

Without privacy protection:

• *Data leakage risk*: raw logs leaking exposes customer information, trade secrets, legal liabilities.
• *Lack of trust*: organizations refuse to share data, blocking collaboration and process improvement.
• *Compliance barriers*: regulations like GDPR restrict data movement, making audits hard.

With privacy protection:

• *Security*: raw data never leaves its domain; cryptography provides guarantees.
• *Collaboration*: cross-organization cooperation without requiring mutual trust.
• *Compliance*: audits satisfy legal requirements and remain legitimate.

4. Takeaway: Knowledge Can Be Shared, Data Doesn't Have to Be Exposed

In the spirit of Feynman—knowing the name of something is different from understanding it:

> Conformance checking doesn't need the *raw data*; it needs the *patterns within the data*. The insight of privacy-preserving process mining is that cryptography lets us extract only the pattern without exposing the data—like knowing the average height without knowing any individual's height.

This captures the essence of privacy computing:

• Data stays put
• Knowledge flows
• Privacy is protected
• Value is extracted

5. Questions to Ask Yourself

If you work with process mining or sensitive data:

1. Does my process audit require exposing raw data? 2. Could privacy-preserving techniques help with compliance? 3. Is secure multi-party computation suitable for my scenario? 4. Can analysis be completed with data staying in its domain?

The paper's lesson: privacy and analysis are not a zero-sum game—cryptography can deliver both.

When process mining learns to check conformance *without seeing*, it transforms from a "data snoop" into a "privacy guardian." In a data-driven future, the best analysis is not the one with the most data, but the one that respects privacy the most.

In the castle of privacy, cryptography is the strongest wall.