# Deep Positive-Negative Prototypes for Adversarially Robust Discriminative Prototypical Learning

arXiv: https://arxiv.org/abs/2504.03782 · HTML: https://mlsanity.com/paper/2504.03782/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 3 Apr 2025.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [Bag of Tricks for Adversarial Training](https://mlsanity.com/paper/2010.00467/) (2020)
- [Boosting Adversarial Training with Hypersphere Embedding](https://mlsanity.com/paper/2002.08619/) (2020)
- [Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training](https://mlsanity.com/paper/1907.10764/) (2019)
- [Metric Learning for Adversarial Robustness](https://mlsanity.com/paper/1909.00900/) (2019)
- [Improving Adversarial Robustness via Channel-wise Activation Suppressing](https://mlsanity.com/paper/2103.08307/) (2021)
- [Decoupled Kullback-Leibler Divergence Loss](https://mlsanity.com/paper/2305.13948/) (2023)
- [CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection](https://mlsanity.com/paper/2102.05311/) (2021)
- [Feature Separation and Recalibration for Adversarial Robustness](https://mlsanity.com/paper/2303.13846/) (2023)
- [Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks](https://mlsanity.com/paper/2005.09147/) (2020)
- [An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks](https://mlsanity.com/paper/2105.09109/) (2021)
- [Prototype-based interpretation of the functionality of neurons in winner-take-all neural networks](https://mlsanity.com/paper/2008.08750/) (2020)
- [Towards Robust Neural Networks via Orthogonal Diversity](https://mlsanity.com/paper/2010.12190/) (2020)

## Built on by (most cited first, 1 of 1)

- [Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics](https://mlsanity.com/paper/2605.06902/) (2026)

## Abstract (arXiv)

Despite the advantages of discriminative prototype-based methods, their role in adversarial robustness remains underexplored. Meanwhile, current adversarial training methods predominantly focus on robustness against adversarial attacks without explicitly leveraging geometric structures in the latent space, usually resulting in reduced accuracy on the original clean data. We propose a novel framework named Adversarially trained Deep Positive-Negative Prototypes (Adv-DPNP), which integrates discriminative prototype-based learning with adversarial training. Adv-DPNP uses unified class prototypes that serve as both classifier weights and robust anchors in the latent space. Moreover, a novel dual-branch training mechanism maintains stable prototypes by updating them exclusively with clean data, while the feature extractor is trained on both clean and adversarial inputs to increase invariance to adversarial perturbations. In addition, we use a composite loss that combines positive-prototype alignment, negative-prototype repulsion, and consistency regularization to further enhance discrimination, adversarial robustness, and clean accuracy. Extensive experiments on standard benchmarks (CIFAR-10/100 and SVHN) confirm that Adv-DPNP improves clean accuracy over state-of-the-art defenses and baseline methods, while maintaining competitive or superior robustness under a suite of widely used attacks, including FGSM, PGD, C&W, and AutoAttack. We also evaluate robustness to common corruptions on CIFAR-10-C, where Adv-DPNP achieves the highest average accuracy across severities and corruption types. Additionally, we provide an in-depth analysis of the discriminative quality of the learned feature representations, highlighting the effectiveness of Adv-DPNP in maintaining compactness and clear separation in the latent space.