English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As a booming research area in the past decade, deep learning technologieshave been driven by big data collected and processed on an unprecedented scale.However, privacy concerns arise due to the potential leakage of sensitiveinformation from the training data. Recent research has revealed that deeplearning models are vulnerable to various privacy attacks, including membershipinference attacks, attribute inference attacks, and gradient inversion attacks.Notably, the efficacy of these attacks varies from model to model. In thispaper, we answer a fundamental question: Does model architecture affect modelprivacy? By investigating representative model architectures from CNNs toTransformers, we demonstrate that Transformers generally exhibit highervulnerability to privacy attacks compared to CNNs. Additionally, We identifythe micro design of activation layers, stem layers, and LN layers, as majorfactors contributing to the resilience of CNNs against privacy attacks, whilethe presence of attention modules is another main factor that exacerbates theprivacy vulnerability of Transformers. Our discovery reveals valuable insightsfor deep learning models to defend against privacy attacks and inspires theresearch community to develop privacy-friendly model architectures.

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers