mlsanityData to 7 Oct 2026

Target Training Does Adversarial Training Without Adversarial Samples

arXiv 2102.04836 ↗First posted 9 Feb 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural network classifiers are vulnerable to misclassification of adversarial samples, for which the current best defense trains classifiers with adversarial samples. However, adversarial samples are not optimal for steering attack convergence, based on the minimization at the core of adversarial attacks. The minimization perturbation term can be minimized towards 0 by replacing adversarial samples in training with duplicated original samples, labeled differently only for training. Using only original samples, Target Training eliminates the need to generate adversarial samples for training against all attacks that minimize perturbation. In low-capacity classifiers and without using adversarial samples, Target Training exceeds both default CIFAR10 accuracy (84.3%) and current best defense accuracy (below 25%) with 84.8% against CW-L2(kappa=0) attack, and 86.6% against DeepFool. Using adversarial samples against attacks that do not minimize perturbation, Target Training exceeds current best defense (69.1%) with 76.4% against CW-L2(kappa=40) in CIFAR10.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

38 of 49 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016Concrete Problems in AI Safetycited by 1,582
  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. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  10. 2016Universal adversarial perturbationscited by 774
  11. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  12. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
26 more
  1. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  2. 2017One pixel attack for fooling deep neural networkscited by 579
  3. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  4. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  5. 2017Countering Adversarial Images using Input Transformationscited by 517
  6. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  7. 2019On Evaluating Adversarial Robustnesscited by 442
  8. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  9. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  10. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  12. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  13. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  14. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  15. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  16. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  17. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  18. 2017The Space of Transferable Adversarial Examplescited by 156
  19. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
  20. 2018Adversarial Attacks and Defences Competitioncited by 96
  21. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  22. 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
  23. 2015Adversarial Manipulation of Deep Representationscited by 56
  24. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  25. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  26. 2018Are Generative Classifiers More Robust to Adversarial Attacks?cited by 36

Built on by

Not cited yet.