# Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models

arXiv: https://arxiv.org/abs/2410.01948 · HTML: https://mlsanity.com/paper/2410.01948/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2024.

## Built on by (most cited first, 2 of 2)

- [The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation](https://mlsanity.com/paper/2507.05578/) (2025)
- [Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs](https://mlsanity.com/paper/2605.11857/) (2026)

## Abstract (arXiv)

Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP). However, traditional DP training is computationally expensive, and can hurt model performance. Our study explores DP parameter-efficient fine-tuning as a way to mitigate privacy risks with smaller computation and performance costs for ASR models. Through extensive experimentation and progressive optimization, we achieve 4.6%/8.1% word error rate on LibriSpeech clean/other test-sets, setting a new performance benchmark while maintaining (10, 3.52e-6)-DP in fine-tuning a large ASR model with over 600M parameters.