# VerifiableFL: Verifiable Claims for Federated Learning using Exclaves

arXiv: https://arxiv.org/abs/2412.10537 · HTML: https://mlsanity.com/paper/2412.10537/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 79 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [Federated Learning for Emoji Prediction in a Mobile Keyboard](https://mlsanity.com/paper/1906.04329/) (2019)
- [PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments](https://mlsanity.com/paper/2104.14380/) (2021)
- [Proof-of-Learning: Definitions and Practice](https://mlsanity.com/paper/2103.05633/) (2021)
- [NVIDIA FLARE: Federated Learning from Simulation to Real-World](https://mlsanity.com/paper/2210.13291/) (2022)
- [Spectre Attacks: Exploiting Speculative Execution](https://mlsanity.com/paper/1801.01203/) (2018)
- [Understanding the Sparse Vector Technique for Differential Privacy](https://mlsanity.com/paper/1603.01699/) (2016)
- [Granite Guardian](https://mlsanity.com/paper/2412.07724/) (2024)
- [Secure and Efficient Federated Transfer Learning](https://mlsanity.com/paper/1910.13271/) (2019)
- ["Adversarial Examples" for Proof-of-Learning](https://mlsanity.com/paper/2108.09454/) (2021)
- [FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attacks](https://mlsanity.com/paper/2308.05832/) (2023)
- [C-FLAT: Control-FLow ATtestation for Embedded Systems Software](https://mlsanity.com/paper/1605.07763/) (2016)
- [Why and How zk-SNARK Works](https://mlsanity.com/paper/1906.07221/) (2019)
- [LO-FAT: Low-Overhead Control Flow ATtestation in Hardware](https://mlsanity.com/paper/1706.03754/) (2017)
- [ZombieLoad: Cross-Privilege-Boundary Data Sampling](https://mlsanity.com/paper/1905.05726/) (2019)
- [Insecure Until Proven Updated: Analyzing AMD SEV's Remote Attestation](https://mlsanity.com/paper/1908.11680/) (2019)
- [SecFL: Confidential Federated Learning using TEEs](https://mlsanity.com/paper/2110.00981/) (2021)

## Built on by (most cited first, 1 of 1)

- [PoCoFL: POlicy-COmpliant Federated Learning](https://mlsanity.com/paper/2610.03650/) (2026)

## Abstract (arXiv)

In federated learning (FL), data providers jointly train a machine learning model without sharing their training data. This makes it challenging to provide verifiable claims about the trained FL model, e.g., related to the employed training data, any data sanitization, or the correct training algorithm-a malicious data provider can simply deviate from the correct training protocol without detection. While prior FL training systems have explored the use of trusted execution environments (TEEs) to protect the training computation, such approaches rely on the confidentiality and integrity of TEEs. The confidentiality guarantees of TEEs, however, have been shown to be vulnerable to a wide range of attacks, such as side-channel attacks. We describe VerifiableFL, a system for training FL models that establishes verifiable claims about trained FL models with the help of fine-grained runtime attestation proofs. Since these runtime attestation proofs only require integrity protection, VerifiableFL generates them using the new abstraction of exclaves. Exclaves are integrity-only execution environments, which do not contain software-managed secrets and thus are immune to data leakage attacks. VerifiableFL uses exclaves to attest individual data transformations during FL training without relying on confidentiality guarantees. The runtime attestation proofs then form an attested dataflow graph of the entire FL model training computation. The graph is checked by an auditor to ensure that the trained FL model satisfies its claims, such as the use of data sanitization by data providers or correct aggregation by the model provider. VerifiableFL extends NVFlare FL framework to use exclaves. We show that VerifiableFL introduces less than 12% overhead compared to unprotected FL training.