SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02718 · 2024

Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures 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/2401.02718.json · badge: /api/ran/2401.02718.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
phenetos/calibrationattack canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
cuda_transfer Ran
ran; our contract draft was wrong, not the code
phenetos/calibrationattack/train_models.py
pointer only (licence: NONE) · get_code("1367aac1053a1fad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

dense_to_onehot Ran
ran; our contract draft was wrong, not the code
phenetos/calibrationattack/utils.py
pointer only (licence: NONE) · get_code("176dfa1e026fb136")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

ensure_numpy Ran
ran, honoured the contract we drafted
phenetos/calibrationattack/recalibration.py
pointer only (licence: NONE) · get_code("2bd69793c2565f55")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

get_aug Ran
ran; our contract draft was wrong, not the code
phenetos/calibrationattack/get_data.py
pointer only (licence: NONE) · get_code("a829230c6819d6c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

get_transform Ran
ran; our contract draft was wrong, not the code
phenetos/calibrationattack/get_data.py
pointer only (licence: NONE) · get_code("b0af5000c1b303cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

get_transform_torchvision Ran
ran; our contract draft was wrong, not the code
phenetos/calibrationattack/get_data.py
pointer only (licence: NONE) · get_code("de59e4240a700352")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

len0 Ran
ran, honoured the contract we drafted
phenetos/calibrationattack/recalibration.py
pointer only (licence: NONE) · get_code("b30c11e674538e2f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

meta_pseudo_gaussian_pert Ran
ran, honoured the contract we drafted
phenetos/calibrationattack/calibration_attack.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, phenetos/calibrationattack 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.

one_hot_encode Ran
ran; our contract draft was wrong, not the code
phenetos/calibrationattack/utils.py
pointer only (licence: NONE) · get_code("77933604fbca56e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

one_hot_encode_v2 Ran
ran; our contract draft was wrong, not the code
phenetos/calibrationattack/utils.py
pointer only (licence: NONE) · get_code("0817f8b0f831deaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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
phenetos/calibrationattack/calibration_attack.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, phenetos/calibrationattack 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
phenetos/calibrationattack/calibration_attack.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, phenetos/calibrationattack 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.

get_model Not yet run
unverified (harvested, no recorded run)
phenetos/calibrationattack/train_models.py
pointer only (licence: NONE) · get_code("f71380bf77811194")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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.

is_numpy_object Not yet run
unverified (harvested, no recorded run)
phenetos/calibrationattack/recalibration.py
pointer only (licence: NONE) · get_code("b6f12dce7894cb0e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phenetos/calibrationattack 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 5 later) and 7 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
one_hot_encode 4 other papers
1 dated earlier, 2 later, 1 undated
2009.03300 (2020-09)
Measuring Massive Multitask Language Understanding
2403.01244 (2024-03)
Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
2601.16503 (2026-01)
MRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine
and 1 more not named here
pseudo_gaussian_pert_rectangles 4 other papers
2 dated earlier, 2 later
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
2406.06979 (2024-06)
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
and 1 more not named here
dense_to_onehot 3 other papers
3 dated earlier
2105.15010 (2021-05)
Query Attack by Multi-Identity Surrogates
2308.11804 (2023-08)
Adversarial Illusions in Multi-Modal Embeddings
2310.00567 (2023-10)
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
meta_pseudo_gaussian_pert 3 other papers
1 dated earlier, 2 later
1912.00049 (2019-12)
Square Attack: a query-efficient black-box adversarial attack via random search
2406.06979 (2024-06)
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
2602.08679 (2026-02)
Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
p_selection 3 other papers
1 dated earlier, 2 later
1912.00049 (2019-12)
Square Attack: a query-efficient black-box adversarial attack via random search
2406.06979 (2024-06)
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
2602.08679 (2026-02)
Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
ensure_numpy 2 other papers
1 dated earlier, 1 later
2006.12800 (2020-06)
Calibration of Neural Networks using Splines
2404.13016 (2024-04)
Optimizing Calibration by Gaining Aware of Prediction Correctness
cuda_transfer 1 other paper
1 dated earlier
2012.03107 (2020-12)
When Do Curricula Work?

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

In this work, we highlight and perform a comprehensive study on calibration attacks, a form of adversarial attacks that aim to trap victim models to be heavily miscalibrated without altering their predicted labels, hence endangering the trustworthiness of the models and follow-up decision making based on their confidence. We propose four typical forms of calibration attacks: underconfidence, overconfidence, maximum miscalibration, and random confidence attacks, conducted in both black-box and white-box setups. We demonstrate that the attacks are highly effective on both convolutional and attention-based models: with a small number of queries, they seriously skew confidence without changing the predictive performance. Given the potential danger, we further investigate the effectiveness of a wide range of adversarial defence and recalibration methods, including our proposed defences specifically designed for calibration attacks to mitigate the harm. From the ECE and KS scores, we observe that there are still significant limitations in handling calibration attacks. To the best of our knowledge, this is the first dedicated study that provides a comprehensive investigation on calibration-focused attacks. We hope this study helps attract more attention to these types of attacks and hence hamper their potential serious damages. To this end, this work also provides detailed analyses to understand the characteristics of the attacks. Our code is available at https://github.com/PhenetOs/CalibrationAttack

For agents

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

get_harvested_code_for_paper("2401.02718")
get_code_for_paper("2401.02718")
have("2401.02718")

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

curl https://syntology.ai/api/ran/2401.02718.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.02718.svg)](https://syntology.ai/paper/2401.02718)

Connect an agent — have() is free.