Implementaiton of "An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models" (ICLR 24)
active 2024-03-10 → 2026-02-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 694 days from 2024-03-10 to 2026-02-01. Pushes: 22 total, peak 8 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 16 total, peak 2 in a day. Comments: 18 total, peak 5 in a day. Stars: 48 total, peak 6 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Haochen-Luo | 34 | 22 | 0 | 8 |
| ranck626 | 9 | 0 | 0 | 6 |
| changbaozhou | 3 | 0 | 0 | 1 |
| asif-hanif | 2 | 0 | 0 | 0 |
| WodenJay | 1 | 0 | 0 | 1 |
| miladabd | 1 | 0 | 0 | 0 |
| TwinkleJing | 1 | 0 | 0 | 1 |
| AGAMPANDEYY | 1 | 0 | 0 | 0 |
| ZS123-lang | 1 | 0 | 0 | 0 |
| Pillowkoh | 1 | 0 | 0 | 1 |
| yechao-zhang | 1 | 0 | 0 | 0 |
| yingpenga | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#4WodenJay2025-04-18 04:51Can train in RTX 4090？
- Issue#11asif-hanif2025-02-17 13:57How are prompts prepared?
- Issue#10AGAMPANDEYY2025-02-14 16:40InstructBLIP error - TypeError: forward() got an unexpected keyword argument 'inputs_embeds'
- Issue#2Haochen-Luo2024-12-14 15:41Missing multiple details about the pretrained network, dataset, missing file and an error on importing the module
- Issue comment#2Haochen-Luo2024-12-07 04:11Missing multiple details about the pretrained network, dataset, missing file and an error on importing the module
- Issue comment#2TwinkleJing2024-12-06 07:34Missing multiple details about the pretrained network, dataset, missing file and an error on importing the module
- Issue#9yingpenga2024-10-08 13:10Why is the target added after the prompt during training?
- Issue comment#8Haochen-Luo2024-10-01 12:51difference between reported and reproduced attack success rates (Table-1)
- Issue#8asif-hanif2024-10-01 10:59difference between reported and reproduced attack success rates (Table-1)
- Issue comment#4Pillowkoh2024-08-12 04:28Can train in RTX 4090？
- Issue comment#7changbaozhou2024-07-16 15:52Question about the Attack method of CroPA.
- Issue#7changbaozhou2024-07-16 15:51Question about the Attack method of CroPA.
- Issue#7changbaozhou2024-07-16 15:11Question about the Attack method of CroPA.
- Issue comment#5Haochen-Luo2024-06-16 07:57Question about dataset of CroPA
- Issue comment#4Haochen-Luo2024-06-16 07:53Can train in RTX 4090？
- Issue comment#6Haochen-Luo2024-06-16 07:50Another missing file：data/img_specific_questions.json
- Issue#6Haochen-Luo2024-06-16 07:50Another missing file：data/img_specific_questions.json
- Issue comment#3ranck6262024-06-13 03:53Missing the file
- Issue#6ranck6262024-06-13 03:49Another missing file：data/img_specific_questions.json
- Issue comment#4ranck6262024-06-12 10:25Can train in RTX 4090？
- Issue comment#5ranck6262024-06-11 15:03Question about dataset of CroPA
- Issue#5ranck6262024-06-11 14:41Question about dataset of CroPA
- Issue comment#3Haochen-Luo2024-06-11 14:38Missing the file
- Issue#3Haochen-Luo2024-06-11 14:38Missing the file
- Issue comment#4Haochen-Luo2024-06-11 14:35Can train in RTX 4090？
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 48 stars here means stars gained during the window, not the repo's star count.