You Only Propagate Once: Painless Adversarial Training Using Maximal Principle
By Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu, Bin Dong. 2019
65 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Adversarial Training and Robustness for Multiple Perturbations (2019, background): “The cost of adversarial training has also be reduced by merging the inner loop of a PGD attack and gradient updates of the model parameters [34, 44], but it is unclear how to extend this approach to a union of perturbations (some of which are not optimized using PGD, e.”
- Adversarial Training for Free! (2019, methodology): “Reference Engstrom et al. [2018] argues that gradient masking adds little security.”
- FreeLB: Enhanced Adversarial Training for Natural Language Understanding (2019, methodology): “In the comparisons with standard PGD (Madry et al., 2018), FreeAT (Shafahi et al., 2019) and YOPO (Zhang et al., 2019), FreeLB stands out to be the best for the datasets and models we evaluated.”
- Fast is better than free: Revisiting adversarial training (2020, methodology): “In response to this difficulty, there has been a recent surge in work that tries to to reduce the complexity of generating an adversarial example, which forms the bulk of the additional computation in adversarial training (Zhang et al., 2019; Shafahi et al., 2019).”
- Intriguing properties of adversarial training (2019, background): “…et al., 2019b; Zhang et al., 2019b; Hendrycks et al., 2019a; Qin et al., 2019; Zhang & Wang, 2019; Carmon et al., 2019; Hendrycks et al., 2019b; Alayrac et al., 2019; Zhai et al., 2019) or accelerate the adversarial training process (Shafahi et al., 2019; Zhang et al., 2019a; Wang & Zhang, 2019).”
- Overfitting in adversarially robust deep learning (2020, methodology): “Robust overfitting is also not specific to PGD-based adversarial training, and affects faster adversarial training methods such as FGSM adversarial training 3 (Wong et al., 2020) as well as top performing algorithms for adversarially robust training such as TRADES (Zhang et al., 2019c).”
- Adversarial Attacks and Defenses in Images, Graphs and Text: A Review (2019, methodology): “Moreover, a number of studies reported the relation between these two properties (Tsipras et al., 2018; Su et al., 2018; Stutz et al., 2019; Zhang et al., 2019b).”
- Adversarially Robust Distillation (2019, methodology): “Finally, with the recent publication of fast adversarial training methods (Shafahi et al. 2019; Zhang et al. 2019a), we hope to further accelerate ARD.”
- Convergence of Adversarial Training in Overparametrized Neural Networks (2019, background): “Also, adversarial training suffers from slow training time since it runs several steps of attacks within one update, and several recent works are trying to resolve this issue [41, 53].”
- FreeLB: Enhanced Adversarial Training for Language Understanding (2019, methodology): “In the comparisons with standard PGD (Madry et al., 2018), FreeAT (Shafahi et al., 2019) and YOPO (Zhang et al., 2019), FreeLB stands out to be the best for the datasets and models we evaluated.”
- Interpreting Adversarially Trained Convolutional Neural Networks (2019, methodology): “This training method was first proposed by (Goodfellow et al., 2014), which is the most successful approach for building robust models so far for defending adversarial examples (Madry et al., 2018; Sinha et al., 2018; Athalye et al., 2018; Zhang et al., 2019b;a).”