Papers › Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing

Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing

29 Jan 2023arXiv:2301.12554archive 2025-07-28

Yatong Bai, Brendon G. Anderson, Aerin Kim, Somayeh Sojoudi

While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties. This paper significantly alleviates this accuracy-robustness trade-off by mixing the output probabilities of a standard classifier and a robust classifier, where the standard network is optimized for clean accuracy and is not robust in general. We show that the robust base classifier's confidence difference for correct and incorrect examples is the key to this improvement. In addition to providing intuitions and empirical evidence, we theoretically certify the robustness of the mixed classifier under realistic assumptions. Furthermore, we adapt an adversarial input detector into a mixing network that adaptively adjusts the mixture of the two base models, further reducing the accuracy penalty of achieving robustness. The proposed flexible method, termed "adaptive smoothing", can work in conjunction with existing or even future methods that improve clean accuracy, robustness, or adversary detection. Our empirical evaluation considers strong attack methods, including AutoAttack and adaptive attack. On the CIFAR-100 dataset, our method achieves an 85.21% clean accuracy while maintaining a 38.72% ℓ_∞-AutoAttacked (ϵ= 8/255) accuracy, becoming the second most robust method on the RobustBench CIFAR-100 benchmark as of submission, while improving the clean accuracy by ten percentage points compared with all listed models. The code that implements our method is available at https://github.com/Bai-YT/AdaptiveSmoothing.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 8 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 8 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

bai-yt/adaptivesmoothing officialmentioned in papermentioned on GitHubpytorchMITSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
codelion/adaptive-classifier pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Overcoming catastrophic forgetting in neural networks (arXiv:1612.00796; that paper's own run record: 16 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified) and Transformer-Squared: Self-adaptive LLMs (arXiv:2501.06252; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

8 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran
2unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from bai-yt/adaptivesmoothing. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

bai-yt/adaptivesmoothing official repository 8 samples, 6 ran (0 instrument-failed) · 2 unverified
L1_projection in 8 papers comp_autoattack/autopgd_base.py ran fingerprinted MIT (permissive) · 1c16a011a0349571 · report fixture: signature x2:Tensor/2/float, y2:Tensor/2/float, eps1:float/0/float · returned Tensor · level recorded 2026-09-25
assemble_data adaptive_smoothing/prepare_data.py ran MIT (permissive) · 4734cca6699e8aac · report fixture: signature imageset:list/1/Tensor, labelset:list/1/Tensor, nested:bool/0/bool · returned tuple · level recorded 2026-09-25
check_range_output comp_autoattack/checks.py ran MIT (permissive) · f219074d942e3b32 · report fixture: signature model:callable/0/?, x:Tensor/2/float, alpha:float/0/float, logger:SimpleLogger/0/? · returned int · level recorded 2026-09-25
load_data in 700 papers adaptive_smoothing/prepare_data.py ran MIT (permissive) · 070460386bfb8f43 · report fixture: signature load_path:str/0/str · returned tuple · level recorded 2026-09-25
pgd_update adaptive_smoothing/attacks.py ran MIT (permissive) · cc49f7b6dd72223e · report fixture: signature images:Tensor/4/float, ori_images:Tensor/4/float, pgd_type:str/0/str, pgd_alpha:float/0/float, pgd_eps:float/0/float, n:int/0/int, momentum:int/0/int · returned tuple · level recorded 2026-09-25
reduce in 14 papers adaptive_smoothing/losses.py ran MIT (permissive) · 849d15297f8360ce · report fixture: signature loss:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-25
comp_pgd_attack adaptive_smoothing/attacks.py unverified MIT (permissive) · 9d155aa2b6ebc707 · report
single_pgd_attack adaptive_smoothing/attacks.py unverified MIT (permissive) · f484c71520aed670 · report

Tasks

Adversarial Robustness

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Adversarial Robustness CIFAR-10 Mixed classifier Accuracy 95.23 #1 of 5 Archive leaderboard report
Adversarial Robustness CIFAR-10 Mixed classifier Attack: AutoAttack 68.06 #1 of 5 Archive leaderboard report
Adversarial Robustness CIFAR-10 Mixed classifier Robust Accuracy 68.06 #1 of 5 Archive leaderboard report
Adversarial Robustness CIFAR-100 Mixed Classifier AutoAttacked Accuracy 38.72 #1 of 2 Archive leaderboard report
Adversarial Robustness CIFAR-100 Mixed Classifier Clean Accuracy 85.21 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

BASE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections