Back to search

Article

Beyond AI: Fooling DNN Model in Physical World

2024-11-13

Abstract excerpt

<title>Abstract</title> <p>Deep neural networks (DNNs) are becoming increasingly crucial across various fields, but their wide adoption raises critical security concerns. This paper proposes an attack that discreetly manipulates model predictions by strategically embedding a tiny patch into the input image. This adversarial patch remains imperceptible to human observers yet effectively compels the model to miscla...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
0bb40c37-6987-5967-8f23-ba352affd64e
DOI
10.21203/rs.3.rs-5352905/v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Beyond AI: Fooling DNN Model in Physical WorldDOI 10.21203/rs.3.rs-5352905/v1
Select a neighboring publication to make it the new centre.