AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems
Not on the map. Why?
Abstract (arXiv)
It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 65 references that are in the map. First posted on arXiv 24 Jun 2022.
Builds on
36 of 65 references.
References · 36
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2022Generative Adversarial Networkscited by 5,627
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Wide Residual Networkscited by 3,070
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
- 2016Adversarial Machine Learning at Scalecited by 936
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
24 more
- 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 787
- 2020Fast is better than free: Revisiting adversarial trainingcited by 727
- 2019Adversarial Training for Free!cited by 643
- 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 574
- 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
- 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 270
- 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
- 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
- 2019Adversarial Training and Robustness for Multiple Perturbationscited by 183
- 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
- 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
- 2018Curriculum Adversarial Trainingcited by 89
- 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
- 2018Universal Adversarial Trainingcited by 87
- 2019Stochastic AUC Maximization with Deep Neural Networkscited by 61
- 2013One-Pass AUC Optimizationcited by 42
- 2018On the Robustness of the CVPR 2018 White-Box Adversarial Example Defensescited by 40
- 2020Calibrated Surrogate Losses for Adversarially Robust Classificationcited by 36
- 2018First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problemscited by 34
- 2018Theoretical Analysis of Adversarial Learning: A Minimax Approachcited by 31
- 2020On the Generalization Properties of Adversarial Trainingcited by 23
- 2022Efficient Global Optimization of Two-Layer ReLU Networks: Quadratic-Time Algorithms and Adversarial Trainingcited by 15
- 2020Variable Smoothing for Weakly Convex Composite Functionscited by 12
- 2018A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classificationcited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.