Adversarial Robustness

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

7 leaderboard tables shown for this task, 7 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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

13 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 788 papers with code (1,746 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Towards Deep Learning Models Resistant to Adversarial Attacks
  19 Jun 2017 59 repositories listed Syntology ran 9 of 17 samples · 8 unverified · 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.
• Certified Adversarial Robustness via Randomized Smoothing
  8 Feb 2019 12 repositories listed
  We 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.
• Generating Adversarial Examples with Adversarial Networks
  8 Jan 2018 10 repositories listed
  A challenge to explore adversarial robustness of neural networks on MNIST.
• Theoretically Principled Trade-off between Robustness and Accuracy
  24 Jan 2019 9 repositories listed Syntology ran 12 of 15 samples · 3 unverified · 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.
• Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
  3 Mar 2020 8 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 4 pointer-only (licence)
  The field of defense strategies against adversarial attacks has significantly grown over the last years, but progress is hampered as the evaluation of adversarial defenses is often insufficient and thus gives a wrong…
• Robustness May Be at Odds with Accuracy
  30 May 2018 8 repositories listed
  We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization.
• Fixing Data Augmentation to Improve Adversarial Robustness
  2 Mar 2021 7 repositories listed
  In particular, against ℓ_∞ norm-bounded perturbations of size ϵ= 8/255, our model reaches 64.
• Adversarial Robustness Toolbox v1.0.0
  3 Jul 2018 7 repositories listed
  Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging…
• Improving Adversarial Robustness via Promoting Ensemble Diversity
  25 Jan 2019 6 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks.
• EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
  13 Sep 2017 6 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to…
• Provably Bounding Neural Network Preimages
  2 Feb 2023 5 repositories listed Syntology ran 0 of 6 samples · 6 unverified · 6 pointer-only (licence)
  Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a nominal input).
• Adversarial Robustness as a Prior for Learned Representations
  3 Jun 2019 5 repositories listed
  In this work, we show that robust optimization can be re-cast as a tool for enforcing priors on the features learned by deep neural networks.
• Improving Alignment and Robustness with Circuit Breakers
  6 Jun 2024 4 repositories listed Syntology ran 3 of 6 samples · 3 unverified · 1 pointer-only (licence)
  Existing techniques aimed at improving alignment, such as refusal training, are often bypassed.
• Decoupled Kullback-Leibler Divergence Loss
  23 May 2023 4 repositories listed Syntology ran 7 of 11 samples · 4 unverified · 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…
• An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
  13 Oct 2022 4 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels.
• Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples
  7 Oct 2020 4 repositories listed
  In the setting with additional unlabeled data, we obtain an accuracy under attack of 65.
• Unlabeled Data Improves Adversarial Robustness
  31 May 2019 4 repositories listed Syntology ran 1 of 8 samples · 7 unverified
  We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning.
• On Evaluating Adversarial Robustness
  18 Feb 2019 4 repositories listed
  Correctly evaluating defenses against adversarial examples has proven to be extremely difficult.
• σ-zero: Gradient-based Optimization of ℓ₀-norm Adversarial Examples
  2 Feb 2024 3 repositories listed Syntology ran 10 of 15 samples · 5 unverified · 13 pointer-only (licence)
  Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging.
• Robust Classification via a Single Diffusion Model
  24 May 2023 3 repositories listed Syntology ran 0 of 3 samples · 3 unverified · 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.
• (Certified!!) Adversarial Robustness for Free!
  21 Jun 2022 3 repositories listed Syntology ran 14 of 34 samples · 20 unverified
  In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models.
• FedNest: Federated Bilevel, Minimax, and Compositional Optimization
  4 May 2022 3 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 2 pointer-only (licence)
  Standard federated optimization methods successfully apply to stochastic problems with single-level structure.
• PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack
  3 Jun 2021 3 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 1 pointer-only (licence)
  In this work, we introduce a fast, general and accurate adversarial attack that optimises the original non-convex constrained minimisation problem.
• Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
  25 Feb 2021 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified.
• Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness
  30 Apr 2020 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  In this work, we propose to employ mode connectivity in loss landscapes to study the adversarial robustness of deep neural networks, and provide novel methods for improving this robustness.
• Adversarial Weight Perturbation Helps Robust Generalization
  13 Apr 2020 3 repositories listed Syntology ran 2 of 5 samples · 3 unverified
  The study on improving the robustness of deep neural networks against adversarial examples grows rapidly in recent years.
• Testing Robustness Against Unforeseen Adversaries
  21 Aug 2019 3 repositories listed Syntology ran 3 of 18 samples · 15 unverified · 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.
• Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
  16 Jun 2019 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Adversarial robustness has become a central goal in deep learning, both in the theory and the practice.
• advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
  20 Feb 2019 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  advertorch is a toolbox for adversarial robustness research.
• Certified Adversarial Robustness with Additive Noise
  10 Sep 2018 3 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs…

Syntology lines on 22 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. Read from the graph 2026-09-24.