HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
jsikyoon
adv_attack_capsnet
Python2017–2017
jsikyoon / adv_attack_capsnet

adv_attack_capsnet

Tensorflow Implementation of Adversarial Attack to Capsule Networks

AI & Machine LearningSystems & InfrastructureNetworking
Explore on GitHubRead Hacker News discussions
2Distinct people
2Mentions
0Explicit recommenders
173GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Tensorflow Implementation of Adversarial Attack to Capsule Networks

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, 1:49:46 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 3-hour interval2 dated mentions

Observed mentions: 2017-11-07 07:01:57 UTC to 2017-11-10 18:58:12 UTC.

012017-11-07 06:00:00 UTC to 2017-11-07 09:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsNov 7, 06:002017-11-07 09:00:00 UTC to 2017-11-07 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-07 12:00:00 UTC to 2017-11-07 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-07 15:00:00 UTC to 2017-11-07 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-07 18:00:00 UTC to 2017-11-07 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-07 21:00:00 UTC to 2017-11-08 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 00:00:00 UTC to 2017-11-08 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 03:00:00 UTC to 2017-11-08 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 06:00:00 UTC to 2017-11-08 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 09:00:00 UTC to 2017-11-08 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 12:00:00 UTC to 2017-11-08 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 15:00:00 UTC to 2017-11-08 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 18:00:00 UTC to 2017-11-08 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-08 21:00:00 UTC to 2017-11-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-09 00:00:00 UTC to 2017-11-09 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsNov 9, 00:002017-11-09 03:00:00 UTC to 2017-11-09 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-09 06:00:00 UTC to 2017-11-09 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-09 09:00:00 UTC to 2017-11-09 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-09 12:00:00 UTC to 2017-11-09 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-09 15:00:00 UTC to 2017-11-09 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-09 18:00:00 UTC to 2017-11-09 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-09 21:00:00 UTC to 2017-11-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-10 00:00:00 UTC to 2017-11-10 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-10 03:00:00 UTC to 2017-11-10 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-10 06:00:00 UTC to 2017-11-10 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-10 09:00:00 UTC to 2017-11-10 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-10 12:00:00 UTC to 2017-11-10 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-10 15:00:00 UTC to 2017-11-10 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-11-10 18:00:00 UTC to 2017-11-10 21:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsNov 10, 18:00

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
Nov 7, 06:002017-11-07 06:00:00 UTC2017-11-07 09:00:00 UTC110
Nov 7, 09:002017-11-07 09:00:00 UTC2017-11-07 12:00:00 UTC000
Nov 7, 12:002017-11-07 12:00:00 UTC2017-11-07 15:00:00 UTC000
Nov 7, 15:002017-11-07 15:00:00 UTC2017-11-07 18:00:00 UTC000
Nov 7, 18:002017-11-07 18:00:00 UTC2017-11-07 21:00:00 UTC000
Nov 7, 21:002017-11-07 21:00:00 UTC2017-11-08 00:00:00 UTC000
Nov 8, 00:002017-11-08 00:00:00 UTC2017-11-08 03:00:00 UTC000
Nov 8, 03:002017-11-08 03:00:00 UTC2017-11-08 06:00:00 UTC000
Nov 8, 06:002017-11-08 06:00:00 UTC2017-11-08 09:00:00 UTC000
Nov 8, 09:002017-11-08 09:00:00 UTC2017-11-08 12:00:00 UTC000
Nov 8, 12:002017-11-08 12:00:00 UTC2017-11-08 15:00:00 UTC000
Nov 8, 15:002017-11-08 15:00:00 UTC2017-11-08 18:00:00 UTC000
Nov 8, 18:002017-11-08 18:00:00 UTC2017-11-08 21:00:00 UTC000
Nov 8, 21:002017-11-08 21:00:00 UTC2017-11-09 00:00:00 UTC000
Nov 9, 00:002017-11-09 00:00:00 UTC2017-11-09 03:00:00 UTC000
Nov 9, 03:002017-11-09 03:00:00 UTC2017-11-09 06:00:00 UTC000
Nov 9, 06:002017-11-09 06:00:00 UTC2017-11-09 09:00:00 UTC000
Nov 9, 09:002017-11-09 09:00:00 UTC2017-11-09 12:00:00 UTC000
Nov 9, 12:002017-11-09 12:00:00 UTC2017-11-09 15:00:00 UTC000
Nov 9, 15:002017-11-09 15:00:00 UTC2017-11-09 18:00:00 UTC000
Nov 9, 18:002017-11-09 18:00:00 UTC2017-11-09 21:00:00 UTC000
Nov 9, 21:002017-11-09 21:00:00 UTC2017-11-10 00:00:00 UTC000
Nov 10, 00:002017-11-10 00:00:00 UTC2017-11-10 03:00:00 UTC000
Nov 10, 03:002017-11-10 03:00:00 UTC2017-11-10 06:00:00 UTC000
Nov 10, 06:002017-11-10 06:00:00 UTC2017-11-10 09:00:00 UTC000
Nov 10, 09:002017-11-10 09:00:00 UTC2017-11-10 12:00:00 UTC000
Nov 10, 12:002017-11-10 12:00:00 UTC2017-11-10 15:00:00 UTC000
Nov 10, 15:002017-11-10 15:00:00 UTC2017-11-10 18:00:00 UTC000
Nov 10, 18:002017-11-10 18:00:00 UTC2017-11-10 21:00:00 UTC101

What Hacker News says

2 sources
michaf·Nov 10, 2017
The article mentions pooling layers as one source for the high frequency patterns. Jeffrey Hinton recently introduced capsule networks (https://news.ycombinator.com/item?id=15609402), in part because he wants to get rid of pooling layers. Maybe this approach is effective to counter (at least visually indistinguishable) adversarial examples. edit: ok, someone already tested it, and it does not seem to help that much: https://github.com/jaesik817/adv_attack_capsnet
In Feature Visualization: How neural nets build up their understanding of images

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.