HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
Hyperparticle
one-pixel-attack-keras
Jupyter Notebook2018–2018
Hyperparticle / one-pixel-attack-keras

one-pixel-attack-keras

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

3Distinct people
3Mentions
0Explicit recommenders
1.2KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:03:16 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day3 dated mentions

Observed mentions: 2018-02-23 20:06:24 UTC to 2018-03-19 19:49:31 UTC.

012018-02-23 00:00:00 UTC to 2018-02-24 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsFeb 232018-02-24 00:00:00 UTC to 2018-02-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-02-25 00:00:00 UTC to 2018-02-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-02-26 00:00:00 UTC to 2018-02-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-02-27 00:00:00 UTC to 2018-02-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-02-28 00:00:00 UTC to 2018-03-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-01 00:00:00 UTC to 2018-03-02 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2018-03-02 00:00:00 UTC to 2018-03-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-03 00:00:00 UTC to 2018-03-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-04 00:00:00 UTC to 2018-03-05 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-05 00:00:00 UTC to 2018-03-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-06 00:00:00 UTC to 2018-03-07 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-07 00:00:00 UTC to 2018-03-08 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsMar 72018-03-08 00:00:00 UTC to 2018-03-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-09 00:00:00 UTC to 2018-03-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-10 00:00:00 UTC to 2018-03-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-11 00:00:00 UTC to 2018-03-12 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-12 00:00:00 UTC to 2018-03-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-13 00:00:00 UTC to 2018-03-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-14 00:00:00 UTC to 2018-03-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-15 00:00:00 UTC to 2018-03-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-16 00:00:00 UTC to 2018-03-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-17 00:00:00 UTC to 2018-03-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-18 00:00:00 UTC to 2018-03-19 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-03-19 00:00:00 UTC to 2018-03-20 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsMar 19

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Feb 232018-02-23 00:00:00 UTC2018-02-24 00:00:00 UTC110
Feb 242018-02-24 00:00:00 UTC2018-02-25 00:00:00 UTC000
Feb 252018-02-25 00:00:00 UTC2018-02-26 00:00:00 UTC000
Feb 262018-02-26 00:00:00 UTC2018-02-27 00:00:00 UTC000
Feb 272018-02-27 00:00:00 UTC2018-02-28 00:00:00 UTC000
Feb 282018-02-28 00:00:00 UTC2018-03-01 00:00:00 UTC000
Mar 12018-03-01 00:00:00 UTC2018-03-02 00:00:00 UTC101
Mar 22018-03-02 00:00:00 UTC2018-03-03 00:00:00 UTC000
Mar 32018-03-03 00:00:00 UTC2018-03-04 00:00:00 UTC000
Mar 42018-03-04 00:00:00 UTC2018-03-05 00:00:00 UTC000
Mar 52018-03-05 00:00:00 UTC2018-03-06 00:00:00 UTC000
Mar 62018-03-06 00:00:00 UTC2018-03-07 00:00:00 UTC000
Mar 72018-03-07 00:00:00 UTC2018-03-08 00:00:00 UTC000
Mar 82018-03-08 00:00:00 UTC2018-03-09 00:00:00 UTC000
Mar 92018-03-09 00:00:00 UTC2018-03-10 00:00:00 UTC000
Mar 102018-03-10 00:00:00 UTC2018-03-11 00:00:00 UTC000
Mar 112018-03-11 00:00:00 UTC2018-03-12 00:00:00 UTC000
Mar 122018-03-12 00:00:00 UTC2018-03-13 00:00:00 UTC000
Mar 132018-03-13 00:00:00 UTC2018-03-14 00:00:00 UTC000
Mar 142018-03-14 00:00:00 UTC2018-03-15 00:00:00 UTC000
Mar 152018-03-15 00:00:00 UTC2018-03-16 00:00:00 UTC000
Mar 162018-03-16 00:00:00 UTC2018-03-17 00:00:00 UTC000
Mar 172018-03-17 00:00:00 UTC2018-03-18 00:00:00 UTC000
Mar 182018-03-18 00:00:00 UTC2018-03-19 00:00:00 UTC000
Mar 192018-03-19 00:00:00 UTC2018-03-20 00:00:00 UTC101

What Hacker News says

3 sources
I fully agree with you that after a MOOC you've barely scratched the surface and until you're implementing them yourself then you're not going to jump into a ML job. However personally I view the rest of the opposite way round. Getting through a course on Deep Learning takes months [0]. Then reading through Keras code once you understand the appropriate NNs is easy. For example it takes a while of going through Neural Networks to understand ResNets. But if you understand ResNets then looking though Keras code that creates a ResNet [1] is easy. If I want to build a NN of any sort in Keras I can just Google for it. However there's no simple Googling you can do to teach yourself NN in an easy to follow structured way. [0]: https://www.deeplearning.ai/ [1]: https://github.com/Hyperparticle/one-pixel-attack-keras/blob...
In Machine Learning Crash Course

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.