Fully Homomorphic Encryption (FHE) represents a paradigm shift in cryptography, enabling computation directly on encrypted data and unlocking privacy-critical computation. Despite being increasingly deployed in real platforms, the reliability aspects of FHE systems, especially how they respond to faults, have been mostly neglected. This paper aims to better understand of how FHE computation behaves in the presence of memory faults, both in terms of individual operations as well as at the level of applications, for different FHE schemes. Finally, we investigate how effective traditional and FHE-specific fault mitigation techniques are.