TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Fooling Neural Networks in the Physical World with 3D Adversarial Objects

14 pointsby loganeover 7 years ago

1 comment

mhkaneover 7 years ago
Awesome work !! This breakthrough opens a new avenue! Also appreciate how far you went in terms of developing new algorithms and 3D printing objects ! Would be interesting to see if this can also work with ensemble of neural networks as well as whether fooling an ensemble automatically leads to transformations fooling individual neural nets within it !