mlsanityData to 14 Oct 2026

Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks

arXiv 2111.10844 ↗First posted 21 Nov 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Despite its great success, deep learning severely suffers from robustness; that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones. Inspired by recent advances in brain science, we propose the Denoised Internal Models (DIM), a novel generative autoencoder-based model to tackle this challenge. Simulating the pipeline in the human brain for visual signal processing, DIM adopts a two-stage approach. In the first stage, DIM uses a denoiser to reduce the noise and the dimensions of inputs, reflecting the information pre-processing in the thalamus. Inspired from the sparse coding of memory-related traces in the primary visual cortex, the second stage produces a set of internal models, one for each category. We evaluate DIM over 42 adversarial attacks, showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 47 of its 84 references that are in the map. First posted on arXiv 21 Nov 2021.

Builds on

47 of 84 references.

References · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  10. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  11. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  12. 2016Adversarial examples in the physical worldcited by 1,769
35 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  2. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  3. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  5. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  6. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  7. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  8. 2017Countering Adversarial Images using Input Transformationscited by 520
  9. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  10. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 451
  11. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  12. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  13. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  14. 2015Recent Advances in Convolutional Neural Networkscited by 360
  15. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  16. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  17. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  18. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  19. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  20. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  21. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  22. 2019ME-Net: Towards Effective Adversarial Robustness with Matrix Estimationcited by 65
  23. 2016Achieving Human Parity in Conversational Speech Recognitioncited by 63
  24. 2019Enhancing Adversarial Defense by k-Winners-Take-Allcited by 51
  25. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  26. 2019Accurate, reliable and fast robustness evaluationcited by 43
  27. 2018On the Robustness of the CVPR 2018 White-Box Adversarial Example Defensescited by 40
  28. 2018Are Generative Classifiers More Robust to Adversarial Attacks?cited by 36
  29. 2018Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimationcited by 25
  30. 2019GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classificationcited by 20
  31. 2017On the Limitation of Convolutional Neural Networks in Recognizing Negative Imagescited by 17
  32. 2018Thwarting Adversarial Examples: An L0-RobustSparse Fourier Transformcited by 13
  33. 2019On the Need for Topology-Aware Generative Models for Manifold-Based Defensescited by 7
  34. 2019Can Attention Masks Improve Adversarial Robustness?cited by 5
  35. 2020Fast Differentiable Clipping-Aware Normalization and Rescalingcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attentioncited by 0