SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.08679 · 2026

Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks

Zizheng Guo, Yanzhang Fu, Jizhou Luo

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2602.08679.json · badge: /api/ran/2602.08679.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.

RepositoryRoleRan
fyzdalao/Dashed-Line-Defense canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
meta_pseudo_gaussian_pert Ran
ran, honoured the contract we drafted
fyzdalao/Dashed-Line-Defense/square.py
pointer only (licence: NONE) · get_code("4ca7ef6d76dc7319")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fyzdalao/Dashed-Line-Defense 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.

p_selection Ran
ran, honoured the contract we drafted
fyzdalao/Dashed-Line-Defense/square.py
pointer only (licence: NONE) · get_code("053d874dd6c8872d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fyzdalao/Dashed-Line-Defense 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.

pseudo_gaussian_pert_rectangles Ran
ran, honoured the contract we drafted
fyzdalao/Dashed-Line-Defense/square.py
pointer only (licence: NONE) · get_code("c7544861060c462d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fyzdalao/Dashed-Line-Defense 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.

margin_loss_n Not yet run
unverified (harvested, no recorded run)
fyzdalao/Dashed-Line-Defense/utils.py
pointer only (licence: NOASSERTION) · get_code("07bc6355b124a3c5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, fyzdalao/Dashed-Line-Defense (NOASSERTION). 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.

sample_imagenet Not yet run
unverified (harvested, no recorded run)
fyzdalao/Dashed-Line-Defense/utils.py
pointer only (licence: NOASSERTION) · get_code("4834e43c0dd5ab07")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, fyzdalao/Dashed-Line-Defense (NOASSERTION). 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.

sample_imagenet_every_class Not yet run
unverified (harvested, no recorded run)
fyzdalao/Dashed-Line-Defense/utils.py
pointer only (licence: NOASSERTION) · get_code("06c49272cd2baa4a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, fyzdalao/Dashed-Line-Defense (NOASSERTION). 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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 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.

FunctionAlso present inEarliest-datedOthers named
pseudo_gaussian_pert_rectangles 4 other papers
4 dated earlier
1912.00049 (2019-12)
Square Attack: a query-efficient black-box adversarial attack via random search
2105.15010 (2021-05)
Query Attack by Multi-Identity Surrogates
2401.02718 (2024-01)
Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
and 1 more not named here
meta_pseudo_gaussian_pert 3 other papers
3 dated earlier
1912.00049 (2019-12)
Square Attack: a query-efficient black-box adversarial attack via random search
2401.02718 (2024-01)
Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
2406.06979 (2024-06)
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
p_selection 3 other papers
3 dated earlier
1912.00049 (2019-12)
Square Attack: a query-efficient black-box adversarial attack via random search
2401.02718 (2024-01)
Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
2406.06979 (2024-06)
AudioMarkBench: Benchmarking Robustness of Audio Watermarking

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Score-based query attacks pose a serious threat to deep learning models by crafting adversarial examples (AEs) using only blackbox access to model output scores, iteratively optimizing inputs based on observed loss values. While recent runtime defenses attempt to disrupt this process via output perturbation, most either require access to model parameters or fail when attackers adapt their tactics. In this paper, we first reveal that even the state-of-the-art plug-and-play defense can be bypassed by adaptive attacks, exposing a critical limitation of existing runtime defenses. We then propose Dashed Line Defense (DLD), a plug-and-play postprocessing method specifically designed to withstand adaptive query strategies. By introducing ambiguity in how the observed loss reflects the true adversarial strength of candidate examples, DLD prevents attackers from reliably analyzing and adapting their queries, effectively disrupting the AE generation process. We provide theoretical guarantees of DLD's defense capability and validate its effectiveness through experiments on ImageNet, demonstrating that DLD consistently outperforms prior defenses-even under worst-case adaptive attacks-while preserving the model's predicted labels.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.08679")
get_code_for_paper("2602.08679")
have("2602.08679")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.08679.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.08679.svg)](https://syntology.ai/paper/2602.08679)

Connect an agent — have() is free.