Adversarial Purification

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

Most implemented papers archive 2025-07-28

27 shown of 27 papers with code (65 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.

• Guided Diffusion Model for Adversarial Purification
  30 May 2022 2 repositories listed
  In this paper, we propose a novel purification approach, referred to as guided diffusion model for purification (GDMP), to help protect classifiers from adversarial attacks.
• Diffusion Models for Adversarial Purification
  16 May 2022 2 repositories listed Syntology ran 11 of 23 samples · 12 unverified · 5 pointer-only (licence)
  Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model.
• FlowPure: Continuous Normalizing Flows for Adversarial Purification
  19 May 2025 1 repository listed
  Despite significant advancements in the area, adversarial robustness remains a critical challenge in systems employing machine learning models.
• LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks
  27 Feb 2025 1 repository listed
  This 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.
• VideoPure: Diffusion-based Adversarial Purification for Video Recognition
  25 Jan 2025 1 repository listed
  Given 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…
• Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks
  4 Dec 2024 1 repository listed
  Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions.
• Random Sampling for Diffusion-based Adversarial Purification
  28 Nov 2024 1 repository listed
  Remarkably, under strong attack, our DiffAP even achieves a more than 20% robustness advantage with 10× sampling acceleration.
• High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
  12 Sep 2024 1 repository listed Syntology ran 2 of 6 samples · 4 unverified · 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.
• Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models
  12 Sep 2024 1 repository listed
  In 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.
• Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
  2 Aug 2024 1 repository listed
  In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern.
• Diffusion-based Adversarial Purification for Intrusion Detection
  25 Jun 2024 1 repository listed
  The 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.
• ZeroPur: Succinct Training-Free Adversarial Purification
  5 Jun 2024 1 repository listed Syntology ran 7 of 13 samples · 6 unverified · 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.
• Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
  18 Mar 2024 1 repository listed
  Current defense strategies usually train DNNs for a specific adversarial attack method and can achieve good robustness in defense against this type of adversarial attack.
• PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification
  11 Mar 2024 1 repository listed
  A 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.
• Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
  29 Jan 2024 1 repository listed Syntology ran 14 of 18 samples · 4 unverified · 18 pointer-only (licence)
  The deep neural networks are known to be vulnerable to well-designed adversarial attacks.
• MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks
  11 Dec 2023 1 repository listed
  In this paper, we introduce MalPurifier, a novel adversarial purification framework specifically engineered for Android malware detection.
• Adversarial Purification of Information Masking
  26 Nov 2023 1 repository listed
  Notably, the residual perturbations on the purified image primarily stem from the same-position patch and similar patches of the adversarial sample.
• Diffusion models meet image counter-forensics
  22 Nov 2023 1 repository listed
  We show that diffusion purification methods are well suited for counter-forensics tasks.
• DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
  27 Oct 2023 1 repository listed Syntology ran 18 of 24 samples · 6 unverified · 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.
• Language Guided Adversarial Purification
  19 Sep 2023 1 repository listed
  Adversarial purification using generative models demonstrates strong adversarial defense performance.
• DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing
  28 Aug 2023 1 repository listed Syntology ran 4 of 6 samples · 2 unverified · 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.
• Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models
  31 Jul 2023 1 repository listed
  Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO).
• Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial Robustness
  25 May 2023 1 repository listed
  In 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.
• Robust Evaluation of Diffusion-Based Adversarial Purification
  16 Mar 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  We analyze the current practices and provide a new guideline for measuring the robustness of purification methods against adversarial attacks.
• Defending against Adversarial Audio via Diffusion Model
  2 Mar 2023 1 repository listed
  In this paper, we propose an adversarial purification-based defense pipeline, AudioPure, for acoustic systems via off-the-shelf diffusion models.
• Adversarial purification with Score-based generative models
  11 Jun 2021 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  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…
• Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models
  27 May 2020 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 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…

Syntology lines on 9 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.