Submix: Practical Private Prediction for Large-Scale Language Models
Recent data-extraction attacks have exposed that language models can memorize some training samples verbatim. This is a vulnerability that can compromise the privacy of the model's training data. In this work, we introduce SubMix: a practical protocol for private next-token prediction designed to prevent privacy violations by language models that were fine-tuned on a private corpus after pre-training on a public corpus. We show that SubMix limits the leakage of information that is unique to any individual user in the private corpus via a relaxation of group differentially private prediction. Importantly, SubMix admits a tight, data-dependent privacy accounting mechanism, which allows it to thwart existing data-extraction attacks while maintaining the utility of the language model. SubMix is the first protocol that maintains privacy even when publicly releasing tens of thousands of next-token predictions made by large transformer-based models such as GPT-2.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Model-Agnostic Augmentation for Accurate Graph Classification
Given a graph dataset, how can we augment it for accurate graph classification? Graph augmentation is an essential strategy to improve the performance of graph-based tasks, and has been widely utilized for analyzing web …
ClassificationGraph ClassificationmodelAdaptively Private Next-Token Prediction of Large Language Models
As Large Language Models (LLMs) proliferate, developing privacy safeguards for these models is crucial. One popular safeguard involves training LLMs in a differentially private manner. However, such solutions are shown t…
When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes
Machine learning models have demonstrated promising performance in many areas. However, the concerns that they can be biased against specific demographic groups hinder their adoption in high-stake applications. Thus, it …
ClassificationFairnessDifferentially Private Next-Token Prediction of Large Language Models
Ensuring the privacy of Large Language Models (LLMs) is becoming increasingly important. The most widely adopted technique to accomplish this is DP-SGD, which trains a model to guarantee Differential Privacy (DP). Howeve…
PredictionIndustrial Scale Privacy Preserving Deep Neural Network
Deep Neural Network (DNN) has been showing great potential in kinds of real-world applications such as fraud detection and distress prediction. Meanwhile, data isolation has become a serious problem currently, i.e., diff…
Fraud DetectionPrivacy Preserving