SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.01428 · 2023

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Modern deep learning requires large volumes of data, which could contain sensitive or private information that cannot be leaked. Recent work has shown for homogeneous neural networks a large portion of this training data could be reconstructed with only access to the trained network parameters. While the attack was shown to work empirically, there exists little formal understanding of its effective regime which datapoints are susceptible to reconstruction. In this work, we first build a stronger version of the dataset reconstruction attack and show how it can provably recover the \emph{entire training set} in the infinite width regime. We then empirically study the characteristics of this attack on two-layer networks and reveal that its success heavily depends on deviations from the frozen infinite-width Neural Tangent Kernel limit. Next, we study the nature of easily-reconstructed images. We show that both theoretically and empirically, reconstructed images tend to "outliers" in the dataset, and that these reconstruction attacks can be used for \textit{dataset distillation}, that is, we can retrain on reconstructed images and obtain high predictive accuracy.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.01428")
get_code_for_paper("2302.01428")
have("2302.01428")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.01428.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.01428.svg)](https://syntology.ai/paper/2302.01428)

Connect an agent — have() is free.