Model Stealing Attacks On FHE-based Privacy-Preserving Machine Learning through Adversarial Examples

ePrint Report: Model Stealing Attacks On FHE-based Privacy-Preserving Machine Learning through Adversarial Examples

Bhuvnesh Chaturvedi, Anirban Chakraborty, Ayantika Chatterjee, Debdeep Mukhopadhyay

Classic MLaaS solutions suffer from privacy-related risks since the user is required to send unencrypted data to the server hosting the MLaaS. To alleviate this problem, a thriving line of research has emerged called Privacy-Preserving Machine Learning (PPML) or secure MLaaS solutions that use cryptographic techniques to preserve the privacy of both the input of the client and the …

adversarial attacks data eprint report fhe hosting machine machine learning privacy problem report risks send server server hosting solutions stealing unencrypted unencrypted data