mlsanityData to 14 Oct 2026

A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions

arXiv 2306.04756 ↗First posted 7 Jun 2023cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

An important aspect of developing reliable deep learning systems is devising strategies that make these systems robust to adversarial attacks. There is a long line of work that focuses on developing defenses against these attacks, but recently, researchers have began to study ways to reverse engineer the attack process. This allows us to not only defend against several attack models, but also classify the threat model. However, there is still a lack of theoretical guarantees for the reverse engineering process. Current approaches that give any guarantees are based on the assumption that the data lies in a union of linear subspaces, which is not a valid assumption for more complex datasets. In this paper, we build on prior work and propose a novel framework for reverse engineering of deceptions which supposes that the clean data lies in the range of a GAN. To classify the signal and attack, we jointly solve a GAN inversion problem and a block-sparse recovery problem. For the first time in the literature, we provide deterministic linear convergence guarantees for this problem. We also empirically demonstrate the merits of the proposed approach on several nonlinear datasets as compared to state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 46 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

39 of 46 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2016Wide Residual Networkscited by 3,070
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  8. 2016Universal adversarial perturbationscited by 784
  9. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  10. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  11. 2019Adversarial Training for Free!cited by 643
  12. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
27 more
  1. 2022Diffusion Models for Adversarial Purificationcited by 476
  2. 2021GAN Inversion: A Surveycited by 367
  3. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  4. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  5. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  6. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 291
  7. 2020Loss landscapes and optimization in over-parameterized non-linear systems and neural networkscited by 233
  8. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 183
  9. 2017Generative Adversarial Perturbationscited by 153
  10. 2021Adversarial purification with Score-based generative modelscited by 134
  11. 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
  12. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  13. 2016Error bounds, quadratic growth, and linear convergence of proximal methodscited by 60
  14. 2018Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guaranteescited by 58
  15. 2017Global Guarantees for Enforcing Deep Generative Priors by Empirical Riskcited by 37
  16. 2019Inverting Deep Generative models, One layer at a timecited by 33
  17. 2020Robust Compressed Sensing using Generative Modelscited by 33
  18. 2021A single gradient step finds adversarial examples on random two-layers neural networkscited by 26
  19. 2021Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernelcited by 26
  20. 2021Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descentcited by 21
  21. 2017Generative Adversarial Trainer: Defense to Adversarial Perturbations with GANcited by 20
  22. 2022Reverse Engineering of Imperceptible Adversarial Image Perturbationscited by 17
  23. 2018A Provably Convergent Scheme for Compressive Sensing under Random Generative Priorscited by 15
  24. 2021Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddingscited by 11
  25. 2019Surfing: Iterative optimization over incrementally trained deep networkscited by 5
  26. 2021Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptionscited by 4
  27. 2022Reverse Engineering ℓp attacks: A block-sparse optimization approach with recovery guaranteescited by 4

Built on by

Not cited yet.