Browse State-of-the-Art › Adversarial Defense
Adversarial Defense
216 papers with code · 10 benchmarks · 5 datasets archive 2025-07-28
Competitions with currently unpublished results:
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
10 leaderboard tables shown for this task, 10 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 4 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): CIFAR-10 (3 judged, 0 placed), ImageNet (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
5 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
2 subtasks in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 403 · with a code link: 216 · where Syntology ran a sample: 66 (50 with a run with no instrument failure, 16 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (66 of 403 tagged: 50 with a run with no instrument failure, 16 where every run was a failure of Syntology's instrument)
Page 1 of 5: papers 1 to 100 of 403, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
19 Jun 2017 59 repositories listed Syntology community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified (of 17 harvested samples) · 13 pointer-only (licence)Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
-
28 Mar 2019 14 repositories listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.
-
3 Oct 2016 13 repositories listed Syntology community repositories only · 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified (of 26 harvested samples) · 26 pointer-only (licence)An adversarial example library for constructing attacks, building defenses, and benchmarking both
-
8 Feb 2019 12 repositories listedWe show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the ℓ₂ norm.
-
24 Nov 2015 11 repositories listedIn this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between…
-
24 Jan 2019 9 repositories listed Syntology official (archive's flag): 1 ran · 12 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 15 harvested samples) · 4 pointer-only (licence)We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples.
-
29 Apr 2019 6 repositories listed Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample) · 1 pointer-only (licence)Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks.
-
26 Nov 2018 5 repositories listed Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample) · 1 pointer-only (licence)However, both natural and robust accuracies, in classifying clean and adversarial images, respectively, of the trained robust models are far from satisfactory.
-
17 May 2018 5 repositories listed Syntology official (archive's flag): 1 ran · 2 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; 2 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 4 pointer-only (licence)Defense-GAN is trained to model the distribution of unperturbed images.
-
14 Aug 2017 5 repositories listed Syntology community repositories only · 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 (of 1 harvested sample)However, different from leveraging attack transferability from substitute models, we propose zeroth order optimization (ZOO) based attacks to directly estimate the gradients of the targeted DNN for generating…
-
23 May 2023 4 repositories listed Syntology official (archive's flag): 4 ran · 11 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples) · 4 pointer-only (licence)In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean…
-
18 Feb 2019 4 repositories listedCorrectly evaluating defenses against adversarial examples has proven to be extremely difficult.
-
1 Feb 2018 4 repositories listedWe identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples.
-
29 Jan 2018 4 repositories listedWhile neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs.
-
15 Nov 2017 4 repositories listed Syntology official: harvested, nothing ran · 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) · 5 unverified (of 8 harvested samples) · 1 pointer-only (licence)This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs.
-
4 Aug 2023 3 repositories listedEnsuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques.
-
24 May 2023 3 repositories listed Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)As RDC does not require training on particular adversarial attacks, we demonstrate that it is more generalizable to defend against multiple unseen threats.
-
23 Nov 2020 3 repositories listedPrevious adversarial training raises model robustness under the compromise of accuracy on natural data.
-
2 Jan 2020 3 repositories listed Syntology official (archive's flag): 1 ran · 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 (of 8 harvested samples)There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application domains, therefore, they cannot be…
-
21 Aug 2019 3 repositories listed Syntology official (archive's flag): 15 ran · 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 18 harvested samples) · 3 pointer-only (licence)To narrow in on this discrepancy between research and reality we introduce ImageNet-UA, a framework for evaluating model robustness against a range of unforeseen adversaries, including eighteen new non-L_p attacks.
-
9 Jun 2019 3 repositories listed Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 2 pointer-only (licence)In this paper, we employ adversarial training to improve the performance of randomized smoothing.
-
27 Feb 2019 3 repositories listed Syntology community repositories only · 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 (of 1 harvested sample) · 1 pointer-only (licence)Although adversarial examples and model robustness have been extensively studied in the context of linear models and neural networks, research on this issue in tree-based models and how to make tree-based models robust…
-
20 Feb 2019 3 repositories listed Syntology official: not harvested · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)advertorch is a toolbox for adversarial robustness research.
-
30 Dec 2024 2 repositories listedFace recognition has witnessed remarkable advancements in recent years, thanks to the development of deep learning techniques.
-
10 Sep 2023 2 repositories listedWith the increasing deployment of deep neural networks in safety-critical applications such as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has become a crucial concern in the…
-
10 Aug 2023 2 repositories listed Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 22 harvested samples) · 22 pointer-only (licence)In this study, we develop a general mechanism to increase neural network robustness based on focus analysis.
-
14 Mar 2023 2 repositories listedTo address this problem, we propose a novel image reconstruction framework, termed SMOOTHED UNROLLING (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust…
-
12 Oct 2022 2 repositories listed Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample)In this work, we leverage visual prompting (VP) to improve adversarial robustness of a fixed, pre-trained model at testing time.
-
23 Feb 2022 2 repositories listedAlthough 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks.
-
23 Dec 2021 2 repositories listedWe first show that the commonly-used Fast-AT is equivalent to using a stochastic gradient algorithm to solve a linearized BLO problem involving a sign operation.
-
18 Nov 2021 2 repositories listed Syntology 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 (of 1 harvested sample) · 1 pointer-only (licence)
-
18 Jun 2021 2 repositories listed
-
31 Mar 2021 2 repositories listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 18 harvested samples) · 1 pointer-only (licence)
-
21 Jan 2021 2 repositories listed
-
20 Nov 2020 2 repositories listed
-
22 Jun 2020 2 repositories listed Syntology official (archive's flag): 9 ran · 11 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 14 harvested samples) · 2 pointer-only (licence)
-
12 Apr 2020 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
1 Dec 2019 2 repositories listed
-
17 Nov 2019 2 repositories listed
-
2 May 2019 2 repositories listed
-
23 Mar 2019 2 repositories listed
-
5 Mar 2019 2 repositories listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples)
-
21 Feb 2019 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
9 Dec 2018 2 repositories listed
-
19 Sep 2018 2 repositories listed
-
4 Jul 2018 2 repositories listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 3 pointer-only (licence)
-
8 Dec 2017 2 repositories listed
-
6 Nov 2017 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
8 Nov 2016 2 repositories listed Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 10 harvested samples)
-
21 Oct 2016 2 repositories listed
-
14 Jul 2025 1 repository listed
-
Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking31 May 2025 1 repository listed
-
22 May 2025 1 repository listed
-
19 May 2025 1 repository listed
-
16 May 2025 1 repository listed
-
4 May 2025 1 repository listed
-
4 Mar 2025 1 repository listed
-
25 Jan 2025 1 repository listed
-
7 Nov 2024 1 repository listed
-
4 Nov 2024 1 repository listed
-
30 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified (of 17 harvested samples)
-
16 Oct 2024 1 repository listed
-
23 Sep 2024 1 repository listed
-
14 Sep 2024 1 repository listed
-
21 Aug 2024 1 repository listed
-
8 Jul 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples)
-
28 Jun 2024 1 repository listed
-
21 Jun 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
18 Jun 2024 1 repository listed
-
16 Jun 2024 1 repository listed
-
28 May 2024 1 repository listed
-
24 May 2024 1 repository listed
-
14 May 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
30 Apr 2024 1 repository listed Syntology official (archive's flag): 18 ran · 18 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified (of 22 harvested samples) · 5 pointer-only (licence)
-
16 Apr 2024 1 repository listed Syntology official (archive's flag): 1 ran · 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) · 2 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
19 Mar 2024 1 repository listed
-
18 Mar 2024 1 repository listed
-
15 Mar 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
21 Feb 2024 1 repository listed Syntology official (archive's flag): 1 ran · 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) · 2 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
19 Feb 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples)
-
15 Dec 2023 1 repository listed
-
14 Dec 2023 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 0 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
12 Dec 2023 1 repository listed
-
12 Dec 2023 1 repository listed Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample)
-
6 Dec 2023 1 repository listed
-
19 Oct 2023 1 repository listed
-
12 Oct 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
5 Oct 2023 1 repository listed
-
3 Oct 2023 1 repository listed Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample)
-
21 Sep 2023 1 repository listed
-
19 Sep 2023 1 repository listed
-
11 Sep 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
7 Sep 2023 1 repository listed
-
31 Jul 2023 1 repository listed
-
24 Jul 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 5 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 2 pointer-only (licence)
-
21 Jul 2023 1 repository listed
-
14 Jul 2023 1 repository listed
-
10 Jul 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 11 pointer-only (licence)
-
15 Jun 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
2 Jun 2023 1 repository listed
Syntology lines on 44 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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