SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.12134 · NeurIPS · 2022

Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks

Xiaolin Huang, Cihang Xie, Sizhe Chen, Zhehao Huang, Qinghua Tao, Yingwen Wu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 1 failure of our instrument; 5 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2205.12134.json · badge: /api/ran/2205.12134.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
sizhe-chen/aaa canonical (classifier label)
classifier basis: classifier_2025
4 ran · 5 no recorded run
FunctionStatusWhere it lives
softmax Ran
ran; our contract draft was wrong, not the code
sizhe-chen/aaa/utils.py
pointer only (licence: NONE) · get_code("785d346b27b67e09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

PGDGenerator2 Ran
ran on a synthesized input
sizhe-chen/aaa/attacker.py
pointer only (licence: NONE) · get_code("5b9f23733537643e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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
sizhe-chen/aaa/utils.py
pointer only (licence: NONE) · get_code("d01a60cd25dd6599")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

random_classes_except_current Ran
ran, violated the contract we drafted
sizhe-chen/aaa/utils.py
pointer only (licence: NONE) · get_code("5be54351ad1e34da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

NASSurrogate Not yet run
unverified (harvested, no recorded run)
sizhe-chen/aaa/attacker.py
pointer only (licence: NONE) · get_code("be11f64c59a474ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

PGDGeneratorInfty Not yet run
unverified (harvested, no recorded run)
sizhe-chen/aaa/attacker.py
pointer only (licence: NONE) · get_code("cc64397ce9932968")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

QueryNet Not yet run
unverified (harvested, no recorded run)
sizhe-chen/aaa/attacker.py
pointer only (licence: NONE) · get_code("31557cefffffb529")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

load_model Not yet run
unverified (harvested, no recorded run)
sizhe-chen/aaa/square.py
pointer only (licence: NONE) · get_code("4fc8682d4d57cb91")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

plot_curve Not yet run
unverified (harvested, no recorded run)
sizhe-chen/aaa/square.py
pointer only (licence: NONE) · get_code("98a406e7a10b0a97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sizhe-chen/aaa 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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.

Repositories linked to this paper

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

Abstract

The score-based query attacks (SQAs) pose practical threats to deep neural networks by crafting adversarial perturbations within dozens of queries, only using the model's output scores. Nonetheless, we note that if the loss trend of the outputs is slightly perturbed, SQAs could be easily misled and thereby become much less effective. Following this idea, we propose a novel defense, namely Adversarial Attack on Attackers (AAA), to confound SQAs towards incorrect attack directions by slightly modifying the output logits. In this way, (1) SQAs are prevented regardless of the model's worst-case robustness; (2) the original model predictions are hardly changed, i.e., no degradation on clean accuracy; (3) the calibration of confidence scores can be improved simultaneously. Extensive experiments are provided to verify the above advantages. For example, by setting ∞ = 8/255 on CIFAR-10, our proposed AAA helps WideResNet-28 secure 80.59% accuracy under Square attack (2500 queries), while the best prior defense (i.e., adversarial training) only attains 67.44%. Since AAA attacks SQA's general greedy strategy, such advantages of AAA over 8 defenses can be consistently observed on 8 CIFAR-10/ImageNet models under 6 SQAs, using different attack targets, bounds, norms, losses, and strategies. Moreover, AAA calibrates better without hurting the accuracy.

For agents

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

get_harvested_code_for_paper("2205.12134")
get_code_for_paper("2205.12134")
have("2205.12134")

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

curl https://syntology.ai/api/ran/2205.12134.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.12134.svg)](https://syntology.ai/paper/2205.12134)

Connect an agent — have() is free.