SXGB: Secure and Efficient Vertical Federated XGBoost via Trusted Execution Environments
Bibliographic record
Abstract
Driven by increasingly tighter privacy restrictions, federated learning (FL), involving training global machine learning models over multiple participants while keeping their data localized, has shown its advantages and gained extensive attention. Despite the promising future, security and efficiency remain major concerns hindering its further development. In this paper, we propose a secure and efficient vertical FL scheme for the XGBoost model, named SXGB, in which the trusted execution environments (TEEs) are introduced to improve the efficiency without an additional security assumption. Specifically, we first design a bucket sharing algorithm to encode and secretly share participants' data buckets. Then, through a combination of the TEEs and symmetric homomorphic encryption techniques, we propose a secure split finding algorithm to accurately find the best splits while ensuring the privacy of data inside and outside the enclave. Moreover, a fingerprint verification method is embedded into the split finding algorithm to ensure the honest execution of the training program. A detailed security analysis shows that SXGB can effectively defend against inference and tamper attacks. Extensive experiments demonstrate that SXGB offers at least a 20× improvement in communication efficiency and a 10× speedup of running time compared to existing representative schemes.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".