FucoPVA: An Efficient Video Analytics Framework with Full-Content Privacy Preservation
Bibliographic record
Abstract
The proliferation of surveillance cameras and rapid advances in computer vision greatly improves life and production, while simultaneously escalating critical privacy concerns. Privacy-preserving computation usually incurs huge amount of workload. In practice, recent privacy-preserving video analytics systems usually adopt the identify-then-hide mechanism to balance privacy and efficiency. However, they rely on high-accuracy target detectors and suffer from attacks using surrounding information such as background or dynamics.In this paper, we design FucoPVA, an efficient Full-Content Privacy-preserving Video Analytics framework for surveillance videos with provable security. It protects all pixels in the video to prevent potential attacks that leverage surrounding information. We architect an efficient cryptographic analytic engine by integrating state-of-the-art privacy-preserving CNN protocol with incremental video computation. We also design a secure consumable resource generator against differential attacks. Evaluation on real-world videos demonstrates that FucoPVA achieves 3-4 orders of magnitude reduction in computation time and communication volume compared to existing full-content privacy-preserving protocols using Delphi and CrypTFlow. The code is available at https://github.com/yxtj/FucoPVA.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".