# Securing Private Federated Learning in a Malicious Setting: A Scalable TEE-Based Approach with Client Auditing

arXiv: https://arxiv.org/abs/2509.08709 · HTML: https://mlsanity.com/paper/2509.08709/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 86 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning with Buffered Asynchronous Aggregation](https://mlsanity.com/paper/2106.06639/) (2021)
- [Practical and Private (Deep) Learning without Sampling or Shuffling](https://mlsanity.com/paper/2103.00039/) (2021)
- [Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity](https://mlsanity.com/paper/1811.12469/) (2018)
- [The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2102.06387/) (2021)
- [PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments](https://mlsanity.com/paper/2104.14380/) (2021)
- [Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning](https://mlsanity.com/paper/2002.04156/) (2020)
- [Differentially Private Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2111.09278/) (2021)
- [The Skellam Mechanism for Differentially Private Federated Learning](https://mlsanity.com/paper/2110.04995/) (2021)
- [Federated Learning of Gboard Language Models with Differential Privacy](https://mlsanity.com/paper/2305.18465/) (2023)
- [Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams](https://mlsanity.com/paper/2202.08312/) (2022)
- [Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning](https://mlsanity.com/paper/2211.06530/) (2022)
- [Spectre Attacks: Exploiting Speculative Execution](https://mlsanity.com/paper/1801.01203/) (2018)
- [Prio: Private, Robust, and Scalable Computation of Aggregate Statistics](https://mlsanity.com/paper/1703.06255/) (2017)
- [Private Summation in the Multi-Message Shuffle Model](https://mlsanity.com/paper/2002.00817/) (2020)
- [Correlated Noise Provably Beats Independent Noise for Differentially Private Learning](https://mlsanity.com/paper/2310.06771/) (2023)
- [Federated Learning in Practice: Reflections and Projections](https://mlsanity.com/paper/2410.08892/) (2024)
- [Concurrent Composition of Differential Privacy](https://mlsanity.com/paper/2105.14427/) (2021)
- [A Hassle-free Algorithm for Private Learning in Practice: Don't Use Tree Aggregation, Use BLTs](https://mlsanity.com/paper/2408.08868/) (2024)
- [Concurrent Composition Theorems for Differential Privacy](https://mlsanity.com/paper/2207.08335/) (2022)
- [Mitigating Leakage in Federated Learning with Trusted Hardware](https://mlsanity.com/paper/2011.04948/) (2020)
- [Elephants Do Not Forget: Differential Privacy with State Continuity for Privacy Budget](https://mlsanity.com/paper/2401.17628/) (2024)
- [The Forking Way: When TEEs Meet Consensus](https://mlsanity.com/paper/2412.00706/) (2024)
- [GlassDB: An Efficient Verifiable Ledger Database System Through Transparency](https://mlsanity.com/paper/2207.00944/) (2022)
- [Confidential Consortium Framework: Secure Multiparty Applications with Confidentiality, Integrity, and High Availability](https://mlsanity.com/paper/2310.11559/) (2023)

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

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

## Abstract (arXiv)

In cross-device private federated learning, differentially private follow-the-regularized-leader (DP-FTRL) has emerged as a promising privacy-preserving method. However, existing approaches assume a semi-honest server and have not addressed the challenge of securely removing this assumption. This is due to its statefulness, which becomes particularly problematic in practical settings where clients can drop out or be corrupted. While trusted execution environments (TEEs) might seem like an obvious solution, a straightforward implementation can introduce forking attacks or availability issues due to state management. To address this problem, our paper introduces a novel server extension that acts as a trusted computing base (TCB) to realize maliciously secure DP-FTRL. The TCB is implemented with an ephemeral TEE module on the server side to produce verifiable proofs of server actions. Some clients, upon being selected, participate in auditing these proofs with small additional communication and computational demands. This extension solution reduces the size of the TCB while maintaining the system's scalability and liveness. We provide formal proofs based on interactive differential privacy, demonstrating privacy guarantee in malicious settings. Finally, we experimentally show that our framework adds small constant overhead to clients in several realistic settings.