Papers › Adversarially Learned Anomaly Detection

Adversarially Learned Anomaly Detection

6 Dec 2018arXiv:1812.02288archive 2025-07-28

Houssam Zenati, Manon Romain, Chuan Sheng Foo, Bruno Lecouat, Vijay Ramaseshan Chandrasekhar

Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GANs) are able to model the complex high-dimensional distributions of real-world data, they offer a promising approach to address this challenge. In this work, we propose an anomaly detection method, Adversarially Learned Anomaly Detection (ALAD) based on bi-directional GANs, that derives adversarially learned features for the anomaly detection task. ALAD then uses reconstruction errors based on these adversarially learned features to determine if a data sample is anomalous. ALAD builds on recent advances to ensure data-space and latent-space cycle-consistencies and stabilize GAN training, which results in significantly improved anomaly detection performance. ALAD achieves state-of-the-art performance on a range of image and tabular datasets while being several hundred-fold faster at test time than the only published GAN-based method.

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 37 code samples harvested from 3 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 21 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 27 samples from 2 repositories, 13 ran (12 with no instrument failure; 1 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

houssamzenati/Adversarially-Learned-Anomaly-Detection officialmentioned in papermentioned on GitHubtfMITSyntology: 10 samples, 3 ran (0 instrument-failed) · 7 unverified report
houssamzenati/Efficient-GAN-Anomaly-Detection mentioned on GitHubtfMITSyntology: 12 samples, 6 ran (1 instrument-failed) · 6 unverified report
intrudetection/robevalanodetect mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systems (arXiv:2207.03576; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zahradehghanian97/rcalad mentioned on GitHubtfMITSyntology: 15 samples, 7 ran (0 instrument-failed) · 8 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.

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

37 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 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.

1ran · our draft was wrong
15ran
21unverified

Licence: 1 of the 37 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

houssamzenati/Adversarially-Learned-Anomaly-Detection official repository 10 samples, 3 ran (0 instrument-failed) · 7 unverified
UnPooling2x2ZeroFilled dsebm/arrhythmia_utilities.py ran fingerprinted MIT (permissive) · 16c98f78677d3622 · report fixture: signature x:EagerTensor/4/float · returned SymbolicTensor · level recorded 2026-09-25
leakyReLu alad/arrhythmia_utilities.py ran MIT (permissive) · 9ab9a03c8845e1b6 · report fixture: signature x:EagerTensor/2/float, alpha:float/0/float, name:NoneType/0/? · returned EagerTensor · level recorded 2026-09-25
tricky_multiply dagmm/gmm_utils.py ran MIT (permissive) · ab2ecca101040c0f · report fixture: signature x:EagerTensor/2/float, y:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
compute_energy_and_penalty dagmm/gmm_utils.py unverified MIT (permissive) · 0a4c5dfb27ad5613 · report
decoder in 19 papers alad/cifar10_utilities.py unverified MIT (permissive) · 588ecf2ffb0e1477 · report
discriminator in 10 papers anogan/cifar10_utilities.py unverified MIT (permissive) · 290d624498e73e32 · report
feature_extractor dagmm/arrhythmia_utilities.py unverified MIT (permissive) · 22140fa826526e60 · report
feature_extractor dagmm/kdd_utilities.py unverified MIT (permissive) · 6a940e179e24a433 · report
generator in 11 papers anogan/cifar10_utilities.py unverified MIT (permissive) · 0364d049bacaa4ba · report
tricky_divide dagmm/gmm_utils.py unverified MIT (permissive) · e7c882e9489249ef · report
houssamzenati/Efficient-GAN-Anomaly-Detection community (archive-listed) 12 samples, 6 ran (1 instrument-failed) · 6 unverified
adapt_labels utils/adapt_data.py ran fingerprinted MIT (permissive) · ece5146bbcad537c · report fixture: signature true_labels:ndarray/1/int, label:int/0/int · returned ndarray · level recorded 2026-09-25
create_logdir gan/run_kdd.py ran MIT (permissive) · 48f5e5db2febd2cd · report fixture: signature method:str/0/str, weight:float/0/float, rd:int/0/int · returned str · level recorded 2026-09-25
create_logdir gan/run_mnist.py ran fingerprinted MIT (permissive) · 63b598466b45fd41 · report fixture: signature method:str/0/str, weight:str/0/str, label:str/0/str, rd:str/0/str · returned str · level recorded 2026-09-25
create_logdir bigan/run_kdd.py ran fingerprinted MIT (permissive) · 141272b50496ac09 · report fixture: signature method:str/0/str, weight:str/0/str, rd:str/0/str · returned str · level recorded 2026-09-25
do_prc utils/evaluations.py ran MIT (permissive) · 40cf96e563e1b70c · report fixture: signature scores:list/1/float, true_labels:list/1/int, file_name:str/0/str, directory:str/0/str, plot:bool/0/bool · returned float · level recorded 2026-09-25
get_getter gan/run_kdd.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 10682b8fe32fba68 · report fixture: signature ema:MockEMA/0/? · returned function · level recorded 2026-09-22
decoder in 19 papers bigan/mnist_utilities.py unverified MIT (permissive) · 0058066f81993565 · report
discriminator in 10 papers gan/mnist_utilities.py unverified MIT (permissive) · df492502964e9039 · report
discriminator in 10 papers bigan/mnist_utilities.py unverified MIT (permissive) · 245a2a952f2d0e8d · report
encoder in 30 papers bigan/mnist_utilities.py unverified MIT (permissive) · 2d5132e520862f91 · report
generator in 11 papers gan/mnist_utilities.py unverified MIT (permissive) · c8be7d36155861a7 · report
leakyReLu gan/kdd_utilities.py unverified MIT (permissive) · 0068a65e1a1fd1cc · report
zahradehghanian97/rcalad community (archive-listed) 15 samples, 7 ran (0 instrument-failed) · 8 unverified
adapt_labels_outlier_task utils/adapt_data.py ran fingerprinted MIT (permissive) · 8e7d47fb8107c08b · report fixture: signature true_labels:ndarray/1/int, label:int/0/int · returned ndarray · level recorded 2026-09-26
batch_fill utils/adapt_data.py ran fingerprinted MIT (permissive) · 944987fbbb730364 · report fixture: signature testx:ndarray/3/float, batch_size:int/0/int · returned tuple · level recorded 2026-09-26
do_roc utils/evaluations.py ran MIT (permissive) · 37571eecf35d57d3 · report fixture: signature scores:list/1/float, true_labels:list/1/int, file_name:str/0/str, directory:str/0/str, plot:bool/0/bool · returned float · level recorded 2026-09-26
get_percentile utils/evaluations.py ran fingerprinted MIT (permissive) · 84a71fe751765a4f · report fixture: signature scores:ndarray/1/float, dataset:str/0/str · returned float64 · level recorded 2026-09-26
leakyReLu model/arrhythmia_utilities.py ran MIT (permissive) · c791a8b03c10d46f · report fixture: signature x:SymbolicTensor/2/float, alpha:float/0/float, name:NoneType/0/? · returned SymbolicTensor · level recorded 2026-09-26
predict in 126 papers utils/evaluations.py ran MIT (permissive) · 3edf8bb21f5c9b3f · report fixture: signature scores:Tensor/2/float, threshold:float/0/float · returned Tensor · level recorded 2026-09-26
spectral_norm in 42 papers utils/sn.py ran MIT (permissive) · dcc62ffe48727dfa · report fixture: signature w:SymbolicTensor/3/float, iteration:int/0/int, eps:float/0/float · returned SymbolicTensor · level recorded 2026-09-26
conv2d in 119 papers utils/sn.py unverified MIT (permissive) · fa9320bc97ab15e6 · report
decoder in 19 papers model/arrhythmia_utilities.py unverified MIT (permissive) · 1b36ea33f85ba3fe · report
decoder in 19 papers model/cifar10_utilities.py unverified MIT (permissive) · c1811109c9446dfc · report
decoder in 19 papers model/kdd_utilities.py unverified MIT (permissive) · 8a7f584ff668f466 · report
dense in 22 papers utils/sn.py unverified MIT (permissive) · c49a28c165a5fb0d · report
encoder in 30 papers model/arrhythmia_utilities.py unverified MIT (permissive) · c1248523a95b5975 · report
encoder in 30 papers model/cifar10_utilities.py unverified MIT (permissive) · 8dbc81f0f8961307 · report
encoder in 30 papers model/kdd_utilities.py unverified MIT (permissive) · 27e033164ba1f735 · report

Tasks

Anomaly Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

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