Skip to content

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

active 2024-03-182025-11-06 (UTC)

Partial coverage20,382 / 26,136 hourly files (78%) · 2 absent upstream · 5,751 failed, retryable2023-08-202026-08-13 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
71
Pushes
5
Pull requests
0
Issues
15
Stars
26
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 599 days from 2024-03-18 to 2025-11-06. Pushes: 5 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 15 total, peak 2 in a day. Comments: 23 total, peak 3 in a day. Stars: 26 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

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

ContributorContributionsPushesPRsComments
TreeLLi194013
LuckyCode5205002
Chenyyyyyyyyy4002
KongJiawei12314002
Chenguoz3001
riolys2001
cheny022000
zhangyun-code2002
Haoyan-Guan1100
AlniyatRui1000

Recent activity

Latest issues, pull requests and releases

  • Issue#11cheny022025-11-06 07:22
    Implementation details for AutoAttack on ImageNet subset
  • Issue#11cheny022025-11-06 07:01
    Implementation details for AutoAttack on ImageNet subset
  • Issue#10LuckyCode5202025-05-21 22:48
    About the cw attack
  • Issue comment#10LuckyCode5202025-05-21 22:47
    About the cw attack
  • Issue comment#10TreeLLi2025-05-21 22:02
    About the cw attack
  • Issue#8LuckyCode5202025-03-07 02:04
    About the Few Shot experiment
  • Issue comment#8TreeLLi2025-03-07 01:45
    About the Few Shot experiment
  • Issue#9TreeLLi2025-03-07 01:34
    Some issue of the paper
  • Issue comment#8LuckyCode5202025-03-05 05:51
    About the Few Shot experiment
  • Issue comment#8TreeLLi2025-03-01 15:29
    About the Few Shot experiment
  • Issue comment#9TreeLLi2025-03-01 14:55
    Some issue of the paper
  • Issue#9AlniyatRui2025-03-01 12:56
    Some issue of the paper
  • Issue#8LuckyCode5202025-02-17 04:03
    About the Few Shot experiment
  • Issue#7Chenyyyyyyyyy2024-12-31 13:19
    Details of out-of-distribution
  • Issue comment#7TreeLLi2024-12-31 06:59
    Details of out-of-distribution
  • Issue comment#7Chenyyyyyyyyy2024-12-31 05:49
    Details of out-of-distribution
  • Issue comment#7TreeLLi2024-12-31 01:32
    Details of out-of-distribution
  • Issue comment#7Chenyyyyyyyyy2024-12-29 10:04
    Details of out-of-distribution
  • Issue comment#7TreeLLi2024-12-29 08:31
    Details of out-of-distribution
  • Issue#7Chenyyyyyyyyy2024-12-28 16:34
    Details of out-of-distribution
  • Issue comment#6Chenguoz2024-12-20 07:25
    Clarification on Line 401 in apt.py: Meaning of 'optimized' and its relation to 'perturbed'
  • Issue#6Chenguoz2024-12-20 07:25
    Clarification on Line 401 in apt.py: Meaning of 'optimized' and its relation to 'perturbed'
  • Issue comment#6TreeLLi2024-12-20 07:07
    Clarification on Line 401 in apt.py: Meaning of 'optimized' and its relation to 'perturbed'
  • Issue#6Chenguoz2024-12-20 06:20
    Clarification on Line 401 in apt.py: Meaning of 'optimized' and its relation to 'perturbed'
  • Issue comment#5TreeLLi2024-11-17 07:56
    About how to choose weights and how to train

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 26 stars here means stars gained during the window, not the repo's star count.