# Reaching Data Confidentiality and Model Accountability on the CalTrain

arXiv: https://arxiv.org/abs/1812.03230 · HTML: https://mlsanity.com/paper/1812.03230/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2018.

## Built on by (most cited first, 3 of 3)

- [Security of AI Agents](https://mlsanity.com/paper/2406.08689/) (2024)
- [Separation of Powers in Federated Learning](https://mlsanity.com/paper/2105.09400/) (2021)
- [Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack](https://mlsanity.com/paper/2506.19886/) (2025)

## Abstract (arXiv)

Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusting multi-party participants. Data confidentiality is guaranteed by retaining private training data on each participant's local infrastructure. However, this approach to achieving data confidentiality makes today's DCL designs fundamentally vulnerable to data poisoning and backdoor attacks. It also limits DCL's model accountability, which is key to backtracking the responsible "bad" training data instances/contributors. In this paper, we introduce CALTRAIN, a Trusted Execution Environment (TEE) based centralized multi-party collaborative learning system that simultaneously achieves data confidentiality and model accountability. CALTRAIN enforces isolated computation on centrally aggregated training data to guarantee data confidentiality. To support building accountable learning models, we securely maintain the links between training instances and their corresponding contributors. Our evaluation shows that the models generated from CALTRAIN can achieve the same prediction accuracy when compared to the models trained in non-protected environments. We also demonstrate that when malicious training participants tend to implant backdoors during model training, CALTRAIN can accurately and precisely discover the poisoned and mislabeled training data that lead to the runtime mispredictions.