Integrity Fingerprinting of DNN with Double Black-box Design and Verification. (arXiv:2203.10902v2 [cs.CR] UPDATED)

Cloud-enabled Machine Learning as a Service (MLaaS) has shown enormous
promise to transform how deep learning models are developed and deployed.
Nonetheless, there is a potential risk associated with the use of such services
since a malicious party can modify them to achieve an adverse result.
Therefore, it is imperative for model owners, service providers, and end-users
to verify whether the deployed model has not been tampered with or not. Such
verification requires public verifiability (i.e., fingerprinting patterns are
available …

box design fingerprinting integrity