On the Vulnerability of FHE Computation to Silent Data Corruption

• URL: http://arxiv.org/abs/2603.23253v1
• Date: Tue, 24 Mar 2026 14:18:05 GMT
• Title: On the Vulnerability of FHE Computation to Silent Data Corruption
• Abstract summary: Fully Homomorphic Encryption (FHE) is emerging as a promising foundation for privacy-preserving cloud services.<n>How reliable is FHE computation on real hardware?<n>We conduct a comprehensive evaluation of SDCs in FHE ciphertext computation.
• Score: 14.337553732980814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• On the Sensitivity to Errors in Homomorphic Computing: Single Transient Bit-flip Client-side Error Characterization [1.1187115031487584]
  Homomorphic Encryption (HE) enables computation on encrypted data without decryption and is a key primitive for privacy-preserving computation in sensitive domains such as healthcare, finance, and government.<n>We analyze the sensitivity of HE to bit-level faults, focusing on the CKKS scheme widely used for approximate arithmetic in AI and machine learning workloads.<n>We identify homomorphic multiplication as the most error-sensitive operation in practical HE pipelines and characterize how faults propagate and amplify through it, exposing a critical vulnerability and motivating the need for more resilient HE deployments.
  arXiv  Detail & Related papers  (2026-08-11T17:13:39Z)
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• Detecting and Understanding Vulnerabilities in Fully Homomorphic Encryption Frameworks [14.240598788040051]
  homomorphic encryption (FHE) allows computations to be performed directly on encrypted data without decryption.<n>New generation of specialized frameworks has emerged to translate high-level FHE programs into complex FHE operations.<n> HERTA is the first automated testing tool tailored for FHE frameworks.
  arXiv  Detail & Related papers  (2026-06-21T14:18:49Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search [69.60882125603133]
  We present ReliabilityRAG, a framework for adversarial robustness that explicitly leverages reliability information of retrieved documents.<n>Our work is a significant step towards more effective, provably robust defenses against retrieved corpus corruption in RAG.
  arXiv  Detail & Related papers  (2025-09-27T22:36:42Z)
• Reliability Analysis of Fully Homomorphic Encryption Systems Under Memory Faults [4.342622051185079]
  Homomorphic Encryption (FHE) represents a paradigm shift in cryptography, enabling computation directly on encrypted data and unlocking privacy-critical computation.<n>This paper aims to better understand of how FHE 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.
  arXiv  Detail & Related papers  (2025-09-25T02:40:16Z)
• Characterizing the Sensitivity to Individual Bit Flips in Client-Side Operations of the CKKS Scheme [0.4054550707324753]
  Homomorphic Encryption (HE) enables computation on encrypted data without decryption, making it a cornerstone of privacy-preserving computation in untrusted environments.<n>HE sees growing adoption in sensitive applications such as secure machine learning and confidential data analysis ensuring its robustness against errors becomes critical.
  arXiv  Detail & Related papers  (2025-07-28T14:42:09Z)
• Understanding the Error Sensitivity of Privacy-Aware Computing [0.5494759889025727]
  Homomorphic Encryption (HE) enables secure computation on encrypted data without decryption, allowing a great opportunity for privacy-preserving computation.<n>In this work, we motivate a thorough discussion regarding the sensitivity of HE applications to bit faults and provide a detailed error characterization study of CKKS (Cheon-Kim-Kim-Song)<n> CKKS is one of the most popular HE schemes due to its fixed-point arithmetic support for AI and machine learning applications.
  arXiv  Detail & Related papers  (2025-06-09T17:27:40Z)
• Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems [89.35169042718739]
  collaborative inference enables end users to leverage powerful deep learning models without exposure of sensitive raw data to cloud servers.<n>Recent studies have revealed that these intermediate features may not sufficiently preserve privacy, as information can be leaked and raw data can be reconstructed via model inversion attacks (MIAs)<n>This work first theoretically proves that the conditional entropy of inputs given intermediate features provides a guaranteed lower bound on the reconstruction mean square error (MSE) under any MIA.<n>Then, we derive a differentiable and solvable measure for bounding this conditional entropy based on the Gaussian mixture estimation and propose a conditional entropy algorithm to enhance the inversion robustness
  arXiv  Detail & Related papers  (2025-03-01T07:15:21Z)
• DataSeal: Ensuring the Verifiability of Private Computation on Encrypted Data [14.21750921409931]
  We introduce DataSeal, which combines the low overhead of the algorithm-based fault tolerance (ABFT) technique with the confidentiality of Fully Homomorphic Encryption (FHE) DataSeal achieves much lower overheads for providing computation verifiability for FHE than other techniques that include MAC, ZKP, and TEE.
  arXiv  Detail & Related papers  (2024-10-19T21:19:39Z)
• Reinforcement Learning on Encrypted Data [58.39270571778521]
  We present a preliminary, experimental study of how a DQN agent trained on encrypted states performs in environments with discrete and continuous state spaces. Our results highlight that the agent is still capable of learning in small state spaces even in presence of non-deterministic encryption, but performance collapses in more complex environments.
  arXiv  Detail & Related papers  (2021-09-16T21:59:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.