Domain Private Transformers for Multi-Domain Dialog Systems (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large general purpose language models have demonstrated impressive performance across many different domains, but their outputs are not guaranteed to stay within the domain of a given input prompt. |
| Approach: | They propose to quantify how likely a conditional language model will leak across domains by defining domain privacy as a way to fine-tune a model's privacy. |
| Outcome: | The proposed method has comparable resiliency to methods adapted from recent literature on differentially private language models. |
Similar Papers
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. |
PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models (2024.acl-long)
Copied to clipboard
Haoran Li, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, Yuan Yao, Yangqiu Song
| Challenge: | generative large language models (LLMs) exhibit surprising capability and integrate previous tasks into a unified text generation formulation. |
| Approach: | They propose a privacy evaluation benchmark to quantify the privacy leakage of language models. |
| Outcome: | The proposed benchmark compares PPLMs with different privacy implementations to find out how privacy leakage is handled. |
Private prediction for large-scale synthetic text generation (2024.findings-emnlp)
Copied to clipboard
Kareem Amin, Alex Bie, Weiwei Kong, Alexey Kurakin, Natalia Ponomareva, Umar Syed, Andreas Terzis, Sergei Vassilvitskii
| Challenge: | Existing approaches to generate differentially private text using large language models are classified into several categories. |
| Approach: | They propose a private prediction framework that generates differentially private synthetic text using large language models via private prediction. |
| Outcome: | The proposed approach generates high-quality synthetic data points at reasonable privacy levels while protecting the privacy of users who contributed to the dataset. |
Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)
Copied to clipboard
Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge. |
| Approach: | They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy. |
| Outcome: | The proposed model protects private data while enhancing the model's knowledge. |
Learning and Evaluating a Differentially Private Pre-trained Language Model (2021.findings-emnlp)
Copied to clipboard
Shlomo Hoory, Amir Feder, Avichai Tendler, Sofia Erell, Alon Peled-Cohen, Itay Laish, Hootan Nakhost, Uri Stemmer, Ayelet Benjamini, Avinatan Hassidim, Yossi Matias
| Challenge: | Contextual language models have improved performance but can lead to information leakage . |
| Approach: | They propose a differentially-private word-piece algorithm that allows training a tailored domain-specific vocabulary while maintaining privacy. |
| Outcome: | The proposed model can guarantee privacy while maintaining good model performance. |
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. |
Differentially Private Language Models for Secure Data Sharing (2022.emnlp-main)
Copied to clipboard
| Challenge: | a variety of deanonymization attacks allow the re-identification of individuals from tabular data. |
| Approach: | They propose to train a language model in a differentially private manner and sample data from it . they find that the model generates fluent textual datasets with privacy guarantees . |
| Outcome: | The proposed methods outperform direct classifiers with DP-SGD in the real-world. |
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. |
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. |
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior attempts at measuring leakage of MLMs via membership inference attacks have been inconclusive, implying potential robustness of Mlms to privacy attacks. |
| Approach: | They propose a stronger membership inference attack based on likelihood ratio hypothesis testing that involves an additional MLM to more accurately quantify the privacy risks of memorization in MLMs. |
| Outcome: | The proposed attack improves the AUC of prior membership inference attacks from 0.66 to an alarmingly high 0.90 level on models trained on medical notes. |