Skip to content

This repository presents a compelling case study on the vulnerability of neural networks to targeted deceptions. By using a Convolutional Neural Network (CNN) trained on the MNIST dataset, we demonstrate how a well-trained model can be deceived into misclassifying manipulated input with high confidence.

active 2023-12-272023-12-28 (UTC)

Complete coverage27,078 / 27,080 hourly files (100%) · 2 absent upstream2023-08-152026-09-16 (UTC)
Events
20
Pushes
14
Pull requests
2
Issues
0
Stars
1
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 2 days from 2023-12-27 to 2023-12-28. Pushes: 14 total, peak 8 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
mertkipcak161420

Recent activity

Latest issues, pull requests and releases

  • Pull request#1mertkipcak2023-12-28 04:40
  • Pull request#1mertkipcak2023-12-28 04:38

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.