# SA-ADP: Sensitivity-Aware Adaptive Differential Privacy for Large Language Models

arXiv: https://arxiv.org/abs/2512.01748 · HTML: https://mlsanity.com/paper/2512.01748/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Beyond Memorization: Violating Privacy Via Inference with Large Language Models](https://mlsanity.com/paper/2310.07298/) (2023)
- [Selective Differential Privacy for Language Modeling](https://mlsanity.com/paper/2108.12944/) (2021)
- [Just Fine-tune Twice: Selective Differential Privacy for Large Language Models](https://mlsanity.com/paper/2204.07667/) (2022)
- [Fine-Tuning Large Language Models with User-Level Differential Privacy](https://mlsanity.com/paper/2407.07737/) (2024)
- [What Are the Chances? Explaining the Epsilon Parameter in Differential Privacy](https://mlsanity.com/paper/2303.00738/) (2023)
- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models](https://mlsanity.com/paper/2502.13313/) (2025)
- [DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning](https://mlsanity.com/paper/2101.03218/) (2021)
- [Training Data for Large Language Model](https://mlsanity.com/paper/2411.07715/) (2024)

## Abstract (arXiv)

Despite advances in the use of large language models (LLMs) in downstream tasks, their ability to memorize information has raised privacy concerns. Therefore, protecting personally identifiable information (PII) during LLM training remains a fundamental challenge. Conventional methods like Differential Privacy-Stochastic Gradient Descent (DP-SGD) provide robust privacy protection via uniform noising, protecting PII regardless of its distinct sensitivity. This comes at the expense of the model's utility, leading to a trade-off. In this paper, we propose SA-ADP, a sensitivity-aware approach that allocates noise based on the sensitivity of individual PII. We evaluated our method on four datasets (ABCD, CUSTOMERSIM, Wikitext-2, and UNSW-NB15 ). Our results show that SA-ADP achieves results comparable to the baseline (No-DP) and the conventional DP-SGD. This means that our method did not degrade the model's utility while still maintaining strong privacy protection.