mlsanityData to 14 Oct 2026

Q-TART: Quickly Training for Adversarial Robustness and in-Transferability

arXiv 2204.07024 ↗First posted 14 Apr 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance, Efficiency, and Robustness, using our proposed algorithm Q-TART, Quickly Train for Adversarial Robustness and in-Transferability. Q-TART follows the intuition that samples highly susceptible to noise strongly affect the decision boundaries learned by DNNs, which in turn degrades their performance and adversarial susceptibility. By identifying and removing such samples, we demonstrate improved performance and adversarial robustness while using only a subset of the training data. Through our experiments we highlight Q-TART's high performance across multiple Dataset-DNN combinations, including ImageNet, and provide insights into the complementary behavior of Q-TART alongside existing adversarial training approaches to increase robustness by over 1.3% while using up to 17.9% less training time.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 14 Apr 2022.

Builds on

31 of 44 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  12. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
19 more
  1. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  2. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  3. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  4. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 678
  5. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  6. 2019Adversarial Training for Free!cited by 643
  7. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  8. 2015Deep Learning with Limited Numerical Precisioncited by 376
  9. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 286
  10. 2017Automated Curriculum Learning for Neural Networkscited by 257
  11. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  12. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  13. 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
  14. 2015Online Batch Selection for Faster Training of Neural Networkscited by 122
  15. 2020Convolutional Networks with Dense Connectivitycited by 98
  16. 2018Curriculum Adversarial Trainingcited by 89
  17. 2013Are all training examples equally valuable?cited by 14
  18. 2020Slimming Neural Networks using Adaptive Connectivity Scorescited by 6
  19. 2020Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensationcited by 4

Built on by

Not cited yet.