Seungju Cho, Changick Kim, Junyoung Byun, Myung-Joon Kwon, Hee-Seon Kim
2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2203.09123.json · badge: /api/ran/2203.09123.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| Trustworthy-AI-Group/TransferAttack | community Papers with Code archive |
1 ran · 2 no recorded run |
| dreamflake/ODI | community Papers with Code archive |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| LogitLoss | Ran ran on a synthesized input · constructed an object; no result was computed |
Trustworthy-AI-Group/TransferAttack/transferattack/input_transformation/odi/odi.py code served (permissive licence) · get_code("a232068b30fcc032") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, LogitLoss: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| render_3d_aug_input | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
dreamflake/ODI/attacks.py code served (permissive licence) · get_code("8eecf670a91ea169") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| ODI | Not yet run unverified (harvested, no recorded run) |
Trustworthy-AI-Group/TransferAttack/transferattack/input_transformation/odi/odi.py code served (permissive licence) · get_code("661d070d25e93987") How it ranno invocation recorded. |
| Render3D | Not yet run unverified (harvested, no recorded run) |
Trustworthy-AI-Group/TransferAttack/transferattack/input_transformation/odi/odi.py code served (permissive licence) · get_code("5d242e552a476463") How it ranno invocation recorded. |
Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The transferability of adversarial examples allows the deception on black-box models, and transfer-based targeted attacks have attracted a lot of interest due to their practical applicability. To maximize the transfer success rate, adversarial examples should avoid overfitting to the source model, and image augmentation is one of the primary approaches for this. However, prior works utilize simple image transformations such as resizing, which limits input diversity. To tackle this limitation, we propose the objectbased diverse input (ODI) method that draws an adversarial image on a 3D object and induces the rendered image to be classified as the target class. Our motivation comes from the humans' superior perception of an image printed on a 3D object. If the image is clear enough, humans can recognize the image content in a variety of viewing conditions. Likewise, if an adversarial example looks like the target class to the model, the model should also classify the rendered image of the 3D object as the target class. The ODI method effectively diversifies the input by leveraging an ensemble of multiple source objects and randomizing viewing conditions. In our experimental results on the ImageNet-Compatible dataset, this method boosts the average targeted attack success rate from 28.3% to 47.0% compared to the state-of-the-art methods. We also demonstrate the applicability of the ODI method to adversarial examples on the face verification task and its superior performance improvement. Our code is available at https://github.com/dreamflake/ODI.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.09123")
get_code_for_paper("2203.09123")
have("2203.09123")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.09123.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.09123)
Connect an agent — have() is free.