Papers › Logit Pairing Methods Can Fool Gradient-Based Attacks

Logit Pairing Methods Can Fool Gradient-Based Attacks

29 Oct 2018arXiv:1810.12042archive 2025-07-28

Marius Mosbach, Maksym Andriushchenko, Thomas Trost, Matthias Hein, Dietrich Klakow

Recently, Kannan et al. [2018] proposed several logit regularization methods to improve the adversarial robustness of classifiers. We show that the computationally fast methods they propose - Clean Logit Pairing (CLP) and Logit Squeezing (LSQ) - just make the gradient-based optimization problem of crafting adversarial examples harder without providing actual robustness. We find that Adversarial Logit Pairing (ALP) may indeed provide robustness against adversarial examples, especially when combined with adversarial training, and we examine it in a variety of settings. However, the increase in adversarial accuracy is much smaller than previously claimed. Finally, our results suggest that the evaluation against an iterative PGD attack relies heavily on the parameters used and may result in false conclusions regarding robustness of a model.

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 24 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 24 samples from 1 repository, 3 ran (3 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.

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

uds-lsv/evaluating-logit-pairing-methods officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 24 samples, 3 ran (0 instrument-failed) · 21 unverified 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.

Code Syntology ran Syntology

24 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 21 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.

3ran
21unverified

Licence: 0 of the 24 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 uds-lsv/evaluating-logit-pairing-methods. “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.

uds-lsv/evaluating-logit-pairing-methods official repository 24 samples, 3 ran (0 instrument-failed) · 21 unverified
load_cifar10 in 20 papers mnist_cifar10/utils.py ran Apache-2.0 (permissive) · 80ab7f0d5badcb2c · report fixture: signature batch_size:int/0/int, data_dir:str/0/str, augmentation:bool/0/bool, stddev:float/0/float, adv_subset:int/0/int, workers:int/0/int · returned tuple · level recorded 2026-09-25
load_mnist in 35 papers mnist_cifar10/utils.py ran Apache-2.0 (permissive) · 4131fcb2c408c901 · report fixture: signature batch_size:int/0/int, data_dir:str/0/str, augmentation:bool/0/bool, stddev:float/0/float, adv_subset:int/0/int, workers:int/0/int · returned tuple · level recorded 2026-09-25
num_examples_per_epoch tiny_imagenet/datasets/tiny_imagenet_input.py ran Apache-2.0 (permissive) · 82c2b6eb2545846f · report fixture: signature split:str/0/str · returned int · level recorded 2026-09-25
adversarial_eval mnist_cifar10/train_utils.py unverified Apache-2.0 (permissive) · 8d88c7458d12a344 · report
clean_eval mnist_cifar10/train_utils.py unverified Apache-2.0 (permissive) · 3f622aea1ef8a1a4 · report
create_biases mnist_cifar10/models.py unverified Apache-2.0 (permissive) · 3da530e14d48c054 · report
create_conv2d_weights mnist_cifar10/models.py unverified Apache-2.0 (permissive) · 490fa4d25461b72a · report
create_weights in 6 papers mnist_cifar10/models.py unverified Apache-2.0 (permissive) · 691983021599f82f · report
generate_pgd_common tiny_imagenet/adversarial_attack.py unverified Apache-2.0 (permissive) · 30f41eaf0970534e · report
generate_pgd_ll tiny_imagenet/adversarial_attack.py unverified Apache-2.0 (permissive) · 2419474f5f44dcb2 · report
generate_pgd_rand tiny_imagenet/adversarial_attack.py unverified Apache-2.0 (permissive) · 81e47ab1c6a2da20 · report
get_cifar10 in 13 papers mnist_cifar10/data_loader.py unverified Apache-2.0 (permissive) · 04ff1339b08bf76e · report
get_lr_schedule in 8 papers tiny_imagenet/model_lib.py unverified Apache-2.0 (permissive) · b1dbba539c2d86e5 · report
get_mnist in 10 papers mnist_cifar10/data_loader.py unverified Apache-2.0 (permissive) · 60f00d58b4540401 · report
get_optimizer in 228 papers tiny_imagenet/model_lib.py unverified Apache-2.0 (permissive) · da769e06be080c23 · report
image_preprocessing tiny_imagenet/datasets/imagenet_input.py unverified Apache-2.0 (permissive) · fa0d1c2e6ff14096 · report
imagenet_input tiny_imagenet/datasets/imagenet_input.py unverified Apache-2.0 (permissive) · 5879253ec320b0e2 · report
imagenet_parser tiny_imagenet/datasets/imagenet_input.py unverified Apache-2.0 (permissive) · d65aec16072659e5 · report
model_train mnist_cifar10/train_utils.py unverified Apache-2.0 (permissive) · 69767d95c86f9450 · report
read_tiny_imagenet_annotations tiny_imagenet/tiny_imagenet_converter/converter.py unverified Apache-2.0 (permissive) · 43080682f6ede917 · report
read_training_annotations tiny_imagenet/tiny_imagenet_converter/converter.py unverified Apache-2.0 (permissive) · 694218061904f78b · report
read_validation_annotations tiny_imagenet/tiny_imagenet_converter/converter.py unverified Apache-2.0 (permissive) · 427561f788da200e · report
tiny_imagenet_input tiny_imagenet/datasets/tiny_imagenet_input.py unverified Apache-2.0 (permissive) · d5f94fe48b23242f · report
tiny_imagenet_parser tiny_imagenet/datasets/tiny_imagenet_input.py unverified Apache-2.0 (permissive) · dc5e94702d782007 · report

Tasks

Adversarial Robustness

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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