Loading
Cookies help us deliver our services. By using our services, you agree to our use of cookies. Learn more

crowdAI is shutting down - please read our blog post for more information

NIPS 2018 : Adversarial Vision Challenge (Robust Model Track)

Pitting machine vision models against adversarial attacks.


Completed
1995
Submissions
396
Participants
62421
Views

Reminder : Use of stochastic elements in models is not permitted: given the same input, models must produce exactly the same output. This is an essential rule of this challenge. The participant formerly holding the top-1 position on the leaderboard has been disqualified for violation of this rule.

Announcement : The offline evaluation phase will begin at 21:00 CEST, Monday, 17th September; and hence the challenge will not be accepting submissions for a week. Updates on when we start accepting submissions again will be provided soon on gitter and on the challenge overview page. Please stay tuned.

Δ # Participant Media Median L2 Distance Mean L2 Distance Entries Last Submission (UTC)
01. 10.037 9.331 14 Mon, 17 Sep 2018 04:51
02. 7.168 8.436 55 Fri, 14 Sep 2018 21:51
03. 6.891 8.286 21 Mon, 17 Sep 2018 00:37
04. 6.227 8.156 48 Mon, 17 Sep 2018 06:37
05. 6.193 8.308 12 Wed, 12 Sep 2018 05:12
06. 5.4 6.202 4 Mon, 16 Jul 2018 20:02
07. 4.531 7.001 42 Tue, 4 Sep 2018 00:11
08. 4.309 5.083 91 Sun, 16 Sep 2018 17:18
09. 3.969 5.759 17 Wed, 12 Sep 2018 05:07
10. 3.914 5.029 24 Fri, 14 Sep 2018 20:36

Entries column includes entries not yet graded which, when graded, may affect the contents of this leaderboard.