Skip to content

Official PyTorch implementation of "CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning" @ ICCV 2023

active 2023-09-122026-01-14 (UTC)

Complete coverage26,549 / 26,549 hourly files (100%) · 2 absent upstream2023-08-152026-08-25 (UTC)
Events
112
Pushes
2
Pull requests
0
Issues
25
Stars
29
Forks
3

Activity over time

Daily event counts in the loaded window

Line chart, 856 days from 2023-09-12 to 2026-01-14. Pushes: 2 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 25 total, peak 4 in a day. Comments: 53 total, peak 10 in a day. Stars: 29 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
nishadsinghi352023
2022wannarest10009
tongzhang1118004
wenxian-ok7005
Hritikbansal5003
Seung-B3002
t13071092563002
Yu-shuyan2001
IdealSanXT2002
Maozhen-Zhang2001
jsrdcht1001
JWLiang0071000
98986oiuoy1000

Recent activity

Latest issues, pull requests and releases

  • Issue#11nishadsinghi2025-06-30 17:30
    when i testing asr , what the result displayed in the terminal repersents?
  • Issue#13nishadsinghi2025-06-30 17:29
    I tried using a different dataset, but the ASR is too low.
  • Issue#14nishadsinghi2025-06-30 17:29
    The ASR cannot be calculated in zero-shot testing.
  • Issue#15nishadsinghi2025-06-30 17:29
    data set problem
  • Issue comment#13Hritikbansal2025-05-15 05:40
    I tried using a different dataset, but the ASR is too low.
  • Issue comment#13wenxian-ok2025-05-15 02:28
    I tried using a different dataset, but the ASR is too low.
  • Issue#14wenxian-ok2025-05-14 08:42
    The ASR cannot be calculated in zero-shot testing.
  • Issue comment#13nishadsinghi2025-04-26 15:42
    I tried using a different dataset, but the ASR is too low.
  • Issue#9nishadsinghi2025-04-26 15:41
    How to test ASR instructions?
  • Issue#12nishadsinghi2025-04-26 15:40
    the accuracy was very low
  • Issue comment#10Maozhen-Zhang2025-04-25 01:24
    How to backdoor with random badnet?
  • Issue comment#12nishadsinghi2025-04-10 14:15
    the accuracy was very low
  • Issue comment#12wenxian-ok2025-04-10 14:05
    the accuracy was very low
  • Issue comment#12nishadsinghi2025-04-09 09:12
    the accuracy was very low
  • Issue comment#12wenxian-ok2025-04-09 01:07
    the accuracy was very low
  • Issue comment#12nishadsinghi2025-04-08 22:14
    the accuracy was very low
  • Issue#12wenxian-ok2025-04-08 14:40
    the accuracy was very low
  • Issue comment#9nishadsinghi2025-04-08 13:49
    How to test ASR instructions?
  • Issue comment#9wenxian-ok2025-04-02 14:37
    How to test ASR instructions?
  • Issue comment#9IdealSanXT2025-03-26 07:01
    How to test ASR instructions?
  • Issue comment#9IdealSanXT2025-03-26 06:58
    How to test ASR instructions?
  • Issue comment#5wenxian-ok2025-03-08 08:26
    The generated file is missing some image paths
  • Issue#10nishadsinghi2025-01-07 12:24
    How to backdoor with random badnet?
  • Issue#1198986oiuoy2025-01-05 07:59
    when i testing asr , what the result displayed in the terminal repersents?
  • Issue comment#10nishadsinghi2025-01-02 16:45
    How to backdoor with random badnet?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 29 stars here means stars gained during the window, not the repo's star count.