Yunrui Yu, Xitong Gao, Cheng-Zhong Xu
3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 1 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/2211.08008.json · badge: /api/ran/2211.08008.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 |
|---|---|---|
| lafeat/mora | canonical (classifier label) classifier basis: classifier_2025 |
3 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| Logger | Ran ran on a synthesized input · constructed an object; no result was computed |
lafeat/mora/mora.py pointer only (licence: NONE) · get_code("b468449dd9f01141") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lafeat/mora when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| MORAAttack | Ran ran on a synthesized input · constructed an object; no result was computed |
lafeat/mora/mora.py pointer only (licence: NONE) · get_code("5af849886d2ac3f0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lafeat/mora when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| MORAAttack_targeted | Ran ran on a synthesized input · constructed an object; no result was computed |
lafeat/mora/mora.py pointer only (licence: NONE) · get_code("1879a450678d2658") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lafeat/mora when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| MORA | Not yet run unverified (harvested, no recorded run) |
lafeat/mora/mora.py pointer only (licence: NONE) · get_code("22efaa3219e51a2c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lafeat/mora when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No 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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| Logger brick of this paper's assembly: helper |
2 other papers 1 dated earlier, 1 later · 2 only as an assembly brick |
2203.05154 (2022-03) Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack |
2311.16124 (2023-11) DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification |
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 attacks can deceive neural networks by adding tiny perturbations to their input data. Ensemble defenses, which are trained to minimize attack transferability among sub-models, offer a promising research direction to improve robustness against such attacks while maintaining a high accuracy on natural inputs. We discover, however, that recent state-of-the-art (SOTA) adversarial attack strategies cannot reliably evaluate ensemble defenses, sizeably overestimating their robustness. This paper identifies the two factors that contribute to this behavior. First, these defenses form ensembles that are notably difficult for existing gradientbased method to attack, due to gradient obfuscation. Second, ensemble defenses diversify sub-model gradients, presenting a challenge to defeat all sub-models simultaneously, simply summing their contributions may counteract the overall attack objective; yet, we observe that ensemble may still be fooled despite most sub-models being correct. We therefore introduce MORA, a model-reweighing attack to steer adversarial example synthesis by reweighing the importance of submodel gradients. MORA finds that recent ensemble defenses all exhibit varying degrees of overestimated robustness. Comparing it against recent SOTA white-box attacks, it can converge orders of magnitude faster while achieving higher attack success rates across all ensemble models examined with three different ensemble modes (i.e., ensembling by either softmax, voting or logits). In particular, most ensemble defenses exhibit near or exactly 0% robustness against MORA with ∞ perturbation within 0.02 on CIFAR-10, and 0.01 on CIFAR-100. We make MORA open source with reproducible results and pre-trained models; and provide a leaderboard of ensemble defenses under various attack strategies 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2211.08008")
get_code_for_paper("2211.08008")
have("2211.08008")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2211.08008.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2211.08008)
Connect an agent — have() is free.