On the Vulnerability of FHE Computation to Silent Data Corruption

2026-03-24

AI Summary

This work presents the first systematic evaluation of the vulnerability of fully homomorphic encryption (FHE) to transient faults, which can induce silent data corruption (SDC) in real hardware. Due to the inherent inaccessibility of plaintext during encrypted computation, detecting such errors remains a significant challenge. Through large-scale fault injection experiments combined with theoretical analysis of error propagation, this study reveals the severity and propagation patterns of SDC in FHE ciphertext computations. The findings quantitatively demonstrate the high sensitivity of FHE schemes to transient faults, expose the limitations of existing fault-tolerance mechanisms in FHE contexts, and suggest concrete directions for improvement. This research addresses a critical gap in the reliability assessment of FHE systems, providing foundational insights for developing more resilient homomorphic computing frameworks.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Adversarial Attacks & Robustness
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Fully Homomorphic Encryption (FHE) is rapidly emerging as a promising foundation for privacy-preserving cloud services, enabling computation directly on encrypted data. As FHE implementations mature and begin moving toward practical deployment in domains such as secure finance, biomedical analytics, and privacy-preserving AI, a critical question remains insufficiently explored: how reliable is FHE computation on real hardware? This question is especially important because, compared with plaintext computation, FHE incurs much higher computational overhead, making it more susceptible to transient hardware faults. Moreover, data corruptions are likely to remain silent: the FHE service has no access to the underlying plaintext, causing unawareness even though the corresponding decrypted result has already been corrupted. To this end, we conduct a comprehensive evaluation of SDCs in FHE ciphertext computation. Through large-scale fault-injection experiments, we characterize the vulnerability of FHE to transient faults, and through a theoretical analysis of error-propagation behaviors, we gain deeper algorithmic insight into the mechanisms underlying this vulnerability. We further assess the effectiveness of different fault-tolerance mechanisms for mitigating these faults.

Problem

• Fully Homomorphic Encryption
• Silent Data Corruption
• Transient Faults
• Hardware Reliability
• Encrypted Computation

Innovation

• Fully Homomorphic Encryption
• Silent Data Corruption
• Fault Injection
• Error Propagation
• Fault Tolerance