Skip to content

serre-lab/Adversarial-Alignment

View on GitHub ↗Related repositories →

Scaling-up deep neural networks to improve their performance on ImageNet makes them more tolerant to adversarial attacks, but successful attacks on these models are misaligned with human perception.

active 2023-09-182025-01-23 (UTC)

Complete coverage26,360 / 26,360 hourly files (100%) · 2 absent upstream2023-08-152026-08-17 (UTC)
Events
9
Pushes
0
Pull requests
0
Issues
2
Stars
2
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 494 days from 2023-09-18 to 2025-01-23. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 2 total, peak 1 in a day. Comments: 4 total, peak 2 in a day. Stars: 2 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
NZ422001
drewlinsley2002
TonyFPY1001
study00981000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#2drewlinsley2024-11-18 18:00
    About ClickMe dataset used in the paper
  • Issue comment#2drewlinsley2024-11-18 17:59
    About ClickMe dataset used in the paper
  • Issue#2study00982024-11-15 15:12
    About ClickMe dataset used in the paper
  • Issue comment#1NZ422024-08-12 08:33
    data release request
  • Issue comment#1TonyFPY2024-08-12 07:58
    data release request
  • Issue#1NZ422024-08-08 14:58
    data release request

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2 stars here means stars gained during the window, not the repo's star count.