vFHE: Verifiable Fully Homomorphic Encryption
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Fully Homomorphic Encryption (FHE) is a powerful building block for secure and private applications. However, state-of-the-art FHE schemes do not offer any integrity guarantees, which can lead to devastating correctness and security issues when FHE is deployed in non-trivial settings. In this paper, we take a critical look at existing integrity solutions for FHE, and analyze their (often implicit) threat models, efficiency, and adequacy with real-world FHE deployments. We explore challenges of what we believe is the most flexible and promising integrity solution for FHE: namely, zero-knowledge Succinct Non-interactive ARguments of Knowledge (zkSNARKs); we showcase optimizations for both general-purpose zkSNARKs and zkSNARKs designed for FHE. We then present two software frameworks, circomlib-FHE and zkOpenFHE, which allow practitioners to automatically augment existing FHE pipelines with integrity guarantees. Finally, we leverage our tools to evaluate and compare different approaches to FHE integrity, and discuss open problems that stand in the way of a widespread deployment of FHE in real-world applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it