Secure re-encryption of homomorphically encrypted data

A computer program product for securing homomorphic encrypted data, the computer program product comprising one or more computer readable storage devices and collectively stored program instructions on the one or more computer readable storage devices, the stored program instructions comprising:

• program instructions to receive fully homomorphically encrypted (FHE) information from a client device;
• program instructions to train a machine learning (ML) model using the FHE information, yielding FHE ciphertexts;
• program instructions to apply a first transform to the FHE ciphertexts, yielding obfuscated FHE ciphertexts wherein the first transform alters a frequency of ciphertext information;
• program instructions to send the obfuscated FHE ciphertexts to a secure device;
• program instructions to receive a de-crypted then re-encrypted version of the obfuscated FHE ciphertexts from the secure device;
• program instructions to apply a second transform to the re-encrypted version of the obfuscated FHE ciphertexts yielding de-obfuscated re-encrypted FHE ciphertexts;
• program instructions to train the ML model using the de-obfuscated re-encrypted FHE ciphertexts, yielding FHE ML model parameters;
• and
• program instructions to send the FHE ML model parameters to the client device.

A computer system for securing homomorphic encrypted data, the computer system comprising:

• one or more computer processors;
• one or more computer readable storage devices;
• and
• stored program instructions on the one or more computer readable storage devices for execution by the one or more computer processors, the stored program instructions comprising:
• program instructions to receive fully homomorphically encrypted (FHE) information from a client device;
• program instructions to train a machine learning (ML) model using the FHE information, yielding FHE ciphertexts;
• program instructions to apply a first transform to the FHE ciphertexts, yielding obfuscated FHE ciphertexts wherein the first transform alters a frequency of ciphertext information;
• program instructions to send the obfuscated FHE ciphertexts to a secure device;
• program instructions to receive a de-crypted then re-encrypted version of the obfuscated FHE ciphertexts from the secure device;
• program instructions to apply a second transform to the re-encrypted version of the obfuscated FHE ciphertexts yielding de-obfuscated re-encrypted FHE ciphertexts;
• program instructions to train the ML model using the de-obfuscated re-encrypted FHE ciphertexts, yielding FHE ML model parameters;
• and
• program instructions to send the FHE ML model parameters to the client device.