Browse State-of-the-Art › Adversarial Purification
Adversarial Purification
27 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
A class of adversarial defense methods that remove adversarial perturbations using a generative model.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
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
No dataset record in the archive lists this task.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 65 · with a code link: 27 · where Syntology ran a sample: 7 (7 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (7 of 65 tagged: 7 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 65 of 65, 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.
-
30 May 2022 2 repositories listedIn this paper, we propose a novel purification approach, referred to as guided diffusion model for purification (GDMP), to help protect classifiers from adversarial attacks.
-
16 May 2022 2 repositories listed Syntology official (archive's flag): 2 ran · 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified (of 23 harvested samples) · 9 pointer-only (licence)Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model.
-
19 May 2025 1 repository listedDespite significant advancements in the area, adversarial robustness remains a critical challenge in systems employing machine learning models.
-
27 Feb 2025 1 repository listedThis paper considers an even more realistic evaluation scenario: gray-box attacks, which assume that the attacker knows the architecture and the dataset used to train the target network, but cannot access its gradients.
-
25 Jan 2025 1 repository listedGiven an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving…
-
4 Dec 2024 1 repository listedAttackers can deliberately perturb classifiers' input with subtle noise, altering final predictions.
-
28 Nov 2024 1 repository listedRemarkably, under strong attack, our DiffAP even achieves a more than 20% robustness advantage with 10× sampling acceleration.
-
12 Sep 2024 1 repository listedIn this paper, we systematically investigate the use of DMs for defending against adversarial attacks on sentences and examine the effect of varying forward diffusion steps.
-
12 Sep 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 4 unverified (of 6 harvested samples) · 6 pointer-only (licence)Recently, text-to-image generative models have been misused to create unauthorized malicious images of individuals, posing a growing social problem.
-
2 Aug 2024 1 repository listedIn the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern.
-
25 Jun 2024 1 repository listedThe escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge.
-
5 Jun 2024 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 13 harvested samples) · 13 pointer-only (licence)In this work, we suppose that adversarial images are outliers of the natural image manifold, and the purification process can be considered as returning them to this manifold.
-
18 Mar 2024 1 repository listedCurrent defense strategies usually train DNNs for a specific adversarial attack method and can achieve good robustness in defense against this type of adversarial attack.
-
11 Mar 2024 1 repository listedA typical way to assess a model's robustness is through adversarial attacks, where test-time examples are generated based on gradients to deceive the model.
-
29 Jan 2024 1 repository listed Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 18 harvested samples) · 18 pointer-only (licence)The deep neural networks are known to be vulnerable to well-designed adversarial attacks.
-
11 Dec 2023 1 repository listedIn this paper, we introduce MalPurifier, a novel adversarial purification framework specifically engineered for Android malware detection.
-
26 Nov 2023 1 repository listedNotably, the residual perturbations on the purified image primarily stem from the same-position patch and similar patches of the adversarial sample.
-
22 Nov 2023 1 repository listedWe show that diffusion purification methods are well suited for counter-forensics tasks.
-
27 Oct 2023 1 repository listed Syntology official (archive's flag): 16 ran · 18 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 13 where Syntology's instrument failed) · 6 unverified (of 24 harvested samples) · 21 pointer-only (licence)In particular, we propose a deviated-reconstruction loss at intermediate diffusion steps to induce inaccurate density gradient estimation to tackle the problem of vanishing/exploding gradients.
-
19 Sep 2023 1 repository listedAdversarial purification using generative models demonstrates strong adversarial defense performance.
-
28 Aug 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 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; 3 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)Diffusion models have been leveraged to perform adversarial purification and thus provide both empirical and certified robustness for a standard model.
-
31 Jul 2023 1 repository listedDeep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO).
-
25 May 2023 1 repository listedIn this work, we propose a novel adversarial defence mechanism for image classification - CARSO - blending the paradigms of adversarial training and adversarial purification in a synergistic robustness-enhancing way.
-
16 Mar 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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)We analyze the current practices and provide a new guideline for measuring the robustness of purification methods against adversarial attacks.
-
2 Mar 2023 1 repository listedIn this paper, we propose an adversarial purification-based defense pipeline, AudioPure, for acoustic systems via off-the-shelf diffusion models.
-
11 Jun 2021 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)Recently, an Energy-Based Model (EBM) trained with Markov-Chain Monte-Carlo (MCMC) has been highlighted as a purification model, where an attacked image is purified by running a long Markov-chain using the gradients of…
-
27 May 2020 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)Our contributions are 1) an improved method for training EBM's with realistic long-run MCMC samples, 2) an Expectation-Over-Transformation (EOT) defense that resolves theoretical ambiguities for stochastic defenses and…
-
DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models4 Jun 2025 0 repositories listedVision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to perturbations poses a significant threat to their reliability in real-world applications.
-
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs1 Jun 2025 0 repositories listedRecent advances in large vision-language models (LVLMs) have showcased their remarkable capabilities across a wide range of multimodal vision-language tasks.
-
How Do Diffusion Models Improve Adversarial Robustness?28 May 2025 0 repositories listedRecent findings suggest that diffusion models significantly enhance empirical adversarial robustness.
-
Towards more transferable adversarial attack in black-box manner23 May 2025 0 repositories listed
-
Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain2 May 2025 0 repositories listed
-
Defending Against Frequency-Based Attacks with Diffusion Models15 Apr 2025 0 repositories listed
-
Model-Free Adversarial Purification via Coarse-To-Fine Tensor Network Representation25 Feb 2025 0 repositories listed
-
Gradient-Free Adversarial Purification with Diffusion Models23 Jan 2025 0 repositories listed
-
Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification1 Jan 2025 0 repositories listed
-
Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds11 Dec 2024 0 repositories listed
-
Adversarial Attacks and Robust Defenses in Speaker Embedding based Zero-Shot Text-to-Speech System5 Oct 2024 0 repositories listed
-
Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training23 Sep 2024 0 repositories listed
-
LoRID: Low-Rank Iterative Diffusion for Adversarial Purification12 Sep 2024 0 repositories listed
-
Instant Adversarial Purification with Adversarial Consistency Distillation30 Aug 2024 0 repositories listed
-
MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification20 Aug 2024 0 repositories listed
-
Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information12 Aug 2024 0 repositories listed
-
Adversarially Robust Industrial Anomaly Detection Through Diffusion Model9 Aug 2024 0 repositories listed
-
Large Language Model Sentinel: LLM Agent for Adversarial Purification24 May 2024 0 repositories listed
-
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective22 Apr 2024 0 repositories listed
-
Adversarial purification for no-reference image-quality metrics: applicability study and new methods10 Apr 2024 0 repositories listed
-
Robust Diffusion Models for Adversarial Purification24 Mar 2024 0 repositories listed
-
Adversarial Purification and Fine-tuning for Robust UDC Image Restoration21 Feb 2024 0 repositories listed
-
Adversarial Text Purification: A Large Language Model Approach for Defense5 Feb 2024 0 repositories listed
-
PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks19 Jan 2024 0 repositories listed
-
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model8 Dec 2023 0 repositories listed
-
Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models13 Nov 2023 0 repositories listed
-
Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness28 Oct 2023 0 repositories listed
-
Diffusion-Based Adversarial Purification for Speaker Verification22 Oct 2023 0 repositories listed
-
Advancing Adversarial Robustness Through Adversarial Logit Update29 Aug 2023 0 repositories listed
-
Rapid Plug-in Defenders27 May 2023 0 repositories listed
-
Adversarial Purification with the Manifold Hypothesis26 Oct 2022 0 repositories listed
-
Towards Adversarial Purification using Denoising AutoEncoders29 Aug 2022 0 repositories listed
-
Guided Diffusion Model for Adversarial Purification from Random Noise22 Jun 2022 0 repositories listed
-
Text Adversarial Purification as Defense against Adversarial Attacks27 Mar 2022 0 repositories listed
-
Adversarial Purification through Representation Disentanglement15 Oct 2021 0 repositories listed
-
Online Adversarial Purification based on Self-Supervision23 Jan 2021 0 repositories listed
-
Online Adversarial Purification based on Self-supervised Learning1 Jan 2021 0 repositories listed
Syntology lines on 10 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