Winston Hsu, Chien Cheng, Hung-Ting Su, Chien Chyou
None of the 3 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (3 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/2308.03243.json · badge: /api/ran/2308.03243.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 |
|---|---|---|
| cyclebooster/unsupervised-adversarial-detection-without-extra-model | canonical (classifier label) classifier basis: classifier_2025 |
0 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| compute_fpr | Not yet run unverified (harvested, no recorded run) |
cyclebooster/unsupervised-adversarial-detection-without-extra-model/art_data_metric.py code served (permissive licence) · get_code("f9d901eb67aac287") How it ranno invocation recorded. |
| detect_metric | Not yet run unverified (harvested, no recorded run) |
cyclebooster/unsupervised-adversarial-detection-without-extra-model/art_data_metric.py code served (permissive licence) · get_code("5a5cce5ffb72352f") How it ranno invocation recorded. |
| threshold_choosing | Not yet run unverified (harvested, no recorded run) |
cyclebooster/unsupervised-adversarial-detection-without-extra-model/art_data_metric.py code served (permissive licence) · get_code("6c4859e68f56ff2b") How it ranno invocation recorded. |
Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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.
Adversarial robustness poses a critical challenge in the deployment of deep learning models for real-world applications. Traditional approaches to adversarial training and supervised detection rely on prior knowledge of attack types and access to labeled training data, which is often impractical. Existing unsupervised adversarial detection methods identify whether the target model works properly, but they suffer from bad accuracies owing to the use of common cross-entropy training loss, which relies on unnecessary features and strengthens adversarial attacks. We propose new training losses to reduce useless features and the corresponding detection method without prior knowledge of adversarial attacks. The detection rate (true positive rate) against all given white-box attacks is above 93.9% except for attacks without limits (DF(∞)), while the false positive rate is barely 2.5%. The proposed method works well in all tested attack types and the false positive rates are even better than the methods good at certain types. The source code is available on this GitHub link.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2308.03243")
get_code_for_paper("2308.03243")
have("2308.03243")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2308.03243.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2308.03243)
Connect an agent — have() is free.