Differentially Private In-Context Learning

by   Ashwinee Panda, et al.

An important question in deploying large language models (LLMs) is how to augment LLMs with private data. We propose Differentially Private In-context Learning (DP-ICL) to enable LLMs to adapt to new tasks while maintaining privacy guarantees. DP-ICL performs private inference by establishing noisy consensus over an ensemble of exemplars using the Report-Noisy-Max mechanism. We evaluate DP-ICL on four benchmarks and find that it achieves comparable performance (<2% degradation) with non-private ICL.


page 1

page 2

page 3

page 4


Classical-Quantum Differentially Private Mechanisms Beyond Classical Ones

Let ε>0. An n-tuple (p_i)_i=1^n of probability vectors is called (classi...

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

Data poisoning and backdoor attacks manipulate training data to induce s...

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

We study the problem of in-context learning (ICL) with large language mo...

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank

Personalized PageRank (PPR) is a fundamental tool in unsupervised learni...

"Private Prediction Strikes Back!” Private Kernelized Nearest Neighbors with Individual Renyi Filter

Most existing approaches of differentially private (DP) machine learning...

Differentially Private Decentralized Optimization with Relay Communication

To address the privacy leakage problem in decentralized composite convex...

Please sign up or login with your details

Forgot password? Click here to reset