mlsanityData to 7 Oct 2026

Adaptive Modeling Against Adversarial Attacks

arXiv 2112.12431 ↗First posted 23 Dec 2021cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an adversarially trained model can be further improved if we fine tune this model in inference stage to adapt to the adversarial input, with the extra information in it. We introduce an algorithm that "post trains" the model at inference stage between the original output class and a "neighbor" class, with existing training data. The accuracy of pre-trained Fast-FGSM CIFAR10 classifier base model against white-box projected gradient attack (PGD) can be significantly improved from 46.8% to 64.5% with our algorithm.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 29 references that are in the map. First posted on arXiv 23 Dec 2021.

Builds on

25 of 29 references.

References · 25

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2016Adversarial Machine Learning at Scalecited by 934
  9. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  10. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  11. 2019Adversarial Training for Free!cited by 638
  12. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
13 more
  1. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  2. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  3. 2018Adversarial Logit Pairingcited by 224
  4. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  5. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
  6. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  7. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  8. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  9. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  10. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  11. 2017Generative Adversarial Trainer: Defense to Adversarial Perturbations with GANcited by 20
  12. 2016Learning Adversary-Resistant Deep Neural Networkscited by 9
  13. 2018Towards Query Efficient Black-box Attacks: An Input-free Perspectivecited by 5

Built on by

Not cited yet.