Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution

Understand

Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright.

• In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models.
• Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models.
• However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity.