mlsanityData to 14 Oct 2026

DISCO: Adversarial Defense with Local Implicit Functions

arXiv 2212.05630 ↗First posted 11 Dec 2022cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

The problem of adversarial defenses for image classification, where the goal is to robustify a classifier against adversarial examples, is considered. Inspired by the hypothesis that these examples lie beyond the natural image manifold, a novel aDversarIal defenSe with local impliCit functiOns (DISCO) is proposed to remove adversarial perturbations by localized manifold projections. DISCO consumes an adversarial image and a query pixel location and outputs a clean RGB value at the location. It is implemented with an encoder and a local implicit module, where the former produces per-pixel deep features and the latter uses the features in the neighborhood of query pixel for predicting the clean RGB value. Extensive experiments demonstrate that both DISCO and its cascade version outperform prior defenses, regardless of whether the defense is known to the attacker. DISCO is also shown to be data and parameter efficient and to mount defenses that transfers across datasets, classifiers and attacks.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 126 of its 181 references that are in the map. First posted on arXiv 11 Dec 2022.

Builds on

126 of 181 references.

References · 126

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2017Squeeze-and-Excitation Networkscited by 4,789
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  11. 2016Wide Residual Networkscited by 3,070
  12. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
38 more
  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  11. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  12. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  13. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  14. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  15. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  16. 2016Pixel Recurrent Neural Networkscited by 816
  17. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  18. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  19. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  20. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  21. 2019Adversarial Training for Free!cited by 643
  22. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  23. 2017One pixel attack for fooling deep neural networkscited by 582
  24. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  25. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  26. 2017Countering Adversarial Images using Input Transformationscited by 520
  27. 2020Overfitting in adversarially robust deep learningcited by 506
  28. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  29. 2022Diffusion Models for Adversarial Purificationcited by 476
  30. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  31. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  32. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  33. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  34. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  35. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  36. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  37. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  38. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362

50 most cited of 126 All 126 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 11; 2025: 13; 2026: 2.

34 papers.

Sort:

By area:

  1. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
  2. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  3. 2024Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Modelscited by 38
  4. 2023Enhancing Adversarial Robustness via Score-Based Optimizationcited by 19
  5. 2024MirrorCheck: Efficient Adversarial Defense for Vision-Language Modelscited by 19
  6. 2025AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defensescited by 15
  7. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  8. 2025AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimizationcited by 8
  9. 2024PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attackscited by 6
  10. 2023DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generationcited by 5
  11. 2024Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metricscited by 5
  12. 2024Robustness Reprogramming for Representation Learningcited by 4
22 more
  1. 2023SAIR: Learning Semantic-aware Implicit Representationcited by 3
  2. 2024CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detectioncited by 2
  3. 2025Fast 2DGS: Efficient Image Representation with Deep Gaussian Priorcited by 2
  4. 2023Rapid Plug-in Defenderscited by 1
  5. 2023IRAD: Implicit Representation-driven Image Resampling against Adversarial Attackscited by 1
  6. 2024LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attackscited by 1
  7. 2024ZeroPur: Succinct Training-Free Adversarial Purificationcited by 1
  8. 2024Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Costcited by 1
  9. 2024Random Sampling for Diffusion-based Adversarial Purificationcited by 1
  10. 2025Boosting Adversarial Robustness and Generalization with Dictionary Structurecited by 1
  11. 2025Democratic Training Against Universal Adversarial Perturbationscited by 1
  12. 2025From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprintscited by 1
  13. 2025Provenance Detection for AI-Generated Images: Combining Perceptual Hashing, Homomorphic Encryption, and AI Detection Modelscited by 1
  14. 2025Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMscited by 1
  15. 2025NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysiscited by 1
  16. 2024Sustainable Self-evolution Adversarial Trainingcited by 0
  17. 2025Diffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial Purifiercited by 0
  18. 2025Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examplescited by 0
  19. 2025Leveraging Generalizability of Image-to-Image Translation for Enhanced Adversarial Defensecited by 0
  20. 2025Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecastingcited by 0
  21. 2026WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attackscited by 0
  22. 2026Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMscited by 0