Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Language models can memorize detailed information and patterns, but raise privacy concerns . ANADP reduces the performance gap between regular and DP fine-tuning while maintaining the privacy constraints. |
| Approach: | They propose an algorithm that allocates additive noise based on the importance of model parameters to reduce the performance gap between regular fine-tuning and traditional DP fine- tuning. |
| Outcome: | The proposed algorithm narrows the performance gap between regular fine-tuning and traditional DP fine- tuning while maintaining privacy constraints. |
Similar Papers
Just Fine-tune Twice: Selective Differential Privacy for Large Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to protect language models from privacy leakage suffer from limited user control and low utility . et al., 2018: a novel framework that achieves SDP for state-of-the-art large transformer-based models. |
| Approach: | They propose a framework that applies differential privacy to large language models . they use redacted in-domain data to fine-tune the model with original in- domain data . |
| Outcome: | The proposed framework achieves strong utility compared to baselines. |
DP-FROST: Differentially Private Fine-tuning of Pre-trained Models with Freezing Model Parameters (2025.coling-main)
Copied to clipboard
| Challenge: | Training models with differential privacy has received a lot of attention since it provides theoretical guarantee of privacy preservation. |
| Approach: | They propose methods that fine-tune large-scale pre-trained models with freezing unimportant parameters for downstream tasks while satisfying differential privacy. |
| Outcome: | The proposed methods fine-tune large pre-trained models with freezing unimportant parameters while satisfying differential privacy while preserving their utility. |
Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on the integration of Differential Privacy (DP) into NLP techniques. |
| Approach: | They propose a method for text privatization leveraging language models to rewrite texts . they examine the usability of DP in NLP and its benefits over non-DP approaches . |
| Outcome: | The proposed method is a novel method for text privatization leveraging language models to rewrite texts. |
Selective Differential Privacy for Language Modeling (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to protect sensitive data from leaking are over-pessimistic and undifferentiated. |
| Approach: | They propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility. |
| Outcome: | The proposed privacy-preserving mechanism achieves better utility while remaining safe under various privacy attacks compared to baselines. |
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels (2021.naacl-main)
Copied to clipboard
Fatemehsadat Mireshghallah, Huseyin Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim
| Challenge: | Neural language models have a high capacity for memorization of training samples . however, this can cause privacy degradation and disparate impact on subgroups of users . |
| Approach: | They propose two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy. |
| Outcome: | The proposed methods have favorable utility-privacy trade-off, faster training and uniform treatment of under-represented subgroups. |
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe (2023.acl-long)
Copied to clipboard
Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Hoda Shajari, Huan Sun, David Levitan, Robert Sim
| Challenge: | Privacy concerns have increased in data-driven products due to the tendency of machine learning models to memorize sensitive training data. |
| Approach: | They propose a method for generating useful synthetic text with a formal privacy guarantee by fine-tuning a pretrained generative language model with DP. |
| Outcome: | The proposed method produces synthetic text competitive in terms of utility with its non-private counterpart, while providing strong protection against potential privacy leakages. |
Differentially Private Natural Language Models: Recent Advances and Future Directions (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in deep learning have led to great success in various natural language processing tasks. |
| Approach: | They propose a systematic review of recent advances in DP deep learning models . they discuss some differences and additional challenges of DP-NLP . |
| Outcome: | The proposed method can prevent reconstruction attacks and protect against potential side knowledge while maintaining the privacy of sensitive data. |
On the Impact of Noise in Differentially Private Text Rewriting (2025.findings-naacl)
Copied to clipboard
| Challenge: | a field of text privatization often requires the addition of noise to vector representations of text . however, noise addition leads to considerable utility loss, highlighting one drawback of DP in NLP. |
| Approach: | They propose a sentence-infilling privatization technique that adds noise to vector representations of text to provide privacy guarantees. |
| Outcome: | The proposed method shows that non-DP privatization methods excel in utility preservation and can find an acceptable privacy-utility trade-off, but cannot outperform DP methods in empirical privacy protections. |
One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing research on the efficiency of differentially-private stochastic gradient descent (DP-SGD) in NLP is inconclusive or even counter-intuitive. |
| Approach: | They propose to use differentially-private stochastic gradient descent (DP-SGD) to preserve privacy in NLP by using modern neural models based on BERT and XtremeDistil architectures to conduct extensive experiments. |
| Outcome: | The proposed models and training strategies provide the best trade-off between privacy and performance on different NLP tasks. |
Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLMs require users to submit raw text regardless of its sensitivity, resulting in substantial computational overhead and degrade model performance. |
| Approach: | They propose a new training pipeline that allows a client-side encoder to condition on k-pooled prompt embeddings instead of raw text and a server-side projection module to fine-tune the projection module and LLM on private, domain-specific data using noise-injected embeddables. |
| Outcome: | The proposed approach eliminates the need for transmitting raw prompt text while maintaining a favorable balance between privacy preservation and model utility for both clients and service providers. |