Preserving privacy in large language models: A survey on current threats and solutions
Large Language Models (LLMs) represent a significant advancement in artificial
intelligence, finding applications across various domains. However, their reliance on …
intelligence, finding applications across various domains. However, their reliance on …
Private distribution learning with public data: The view from sample compression
We study the problem of private distribution learning with access to public data. In this setup,
which we refer to as* public-private learning*, the learner is given public and private …
which we refer to as* public-private learning*, the learner is given public and private …
Can Public Large Language Models Help Private Cross-device Federated Learning?
We study (differentially) private federated learning (FL) of language models. The language
models in cross-device FL are relatively small, which can be trained with meaningful formal …
models in cross-device FL are relatively small, which can be trained with meaningful formal …
Differentially private image classification by learning priors from random processes
In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-
SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A …
SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A …
Vip: A differentially private foundation model for computer vision
Artificial intelligence (AI) has seen a tremendous surge in capabilities thanks to the use of
foundation models trained on internet-scale data. On the flip side, the uncurated nature of …
foundation models trained on internet-scale data. On the flip side, the uncurated nature of …
Differentially private synthetic data via foundation model apis 1: Images
Generating differentially private (DP) synthetic data that closely resembles the original
private data is a scalable way to mitigate privacy concerns in the current data-driven world …
private data is a scalable way to mitigate privacy concerns in the current data-driven world …
Private learning with public features
W Krichene, NE Mayoraz, S Rendle… - International …, 2024 - proceedings.mlr.press
We study a class of private learning problems in which the data is a join of private and public
features. This is often the case in private personalization tasks such as recommendation or …
features. This is often the case in private personalization tasks such as recommendation or …
Private fine-tuning of large language models with zeroth-order optimization
Fine-tuning large pretrained models on private datasets may run the risk of violating privacy.
Differential privacy is a framework for mitigating privacy risks by enforcing algorithmic …
Differential privacy is a framework for mitigating privacy risks by enforcing algorithmic …
Unlocking accuracy and fairness in differentially private image classification
Privacy-preserving machine learning aims to train models on private data without leaking
sensitive information. Differential privacy (DP) is considered the gold standard framework for …
sensitive information. Differential privacy (DP) is considered the gold standard framework for …
Choosing public datasets for private machine learning via gradient subspace distance
Differentially private stochastic gradient descent privatizes model training by injecting noise
into each iteration, where the noise magnitude increases with the number of model …
into each iteration, where the noise magnitude increases with the number of model …