# Enhancing Adversarial Robustness through Multi-Objective Representation Learning

arXiv: https://arxiv.org/abs/2410.01697 · HTML: https://mlsanity.com/paper/2410.01697/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (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)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [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)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Understanding and Mitigating the Tradeoff Between Robustness and Accuracy](https://mlsanity.com/paper/2002.10716/) (2020)
- [Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness](https://mlsanity.com/paper/2112.02671/) (2021)
- [Boosting Adversarial Training via Fisher-Rao Norm-based Regularization](https://mlsanity.com/paper/2403.17520/) (2024)
- [Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM](https://mlsanity.com/paper/2403.11448/) (2024)
- [Multi-Objective Optimization for Sparse Deep Multi-Task Learning](https://mlsanity.com/paper/2308.12243/) (2023)
- [GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks](https://mlsanity.com/paper/2302.02907/) (2023)
- [Improving Adversarial Robustness via Decoupled Visual Representation Masking](https://mlsanity.com/paper/2406.10933/) (2024)

## Abstract (arXiv)

Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce drastically different outputs. Many defense methods require modifying model architectures during evaluation or performing test-time data purification. This not only introduces additional complexity but is often architecture-dependent. We show, however, that robust feature learning during training can significantly enhance DNN robustness. We propose MOREL, a multi-objective approach that aligns natural and adversarial features using cosine similarity and multi-positive contrastive losses to encourage similar features for same-class inputs. Extensive experiments demonstrate that MOREL significantly improves robustness against both white-box and black-box attacks. Our code is available at https://github.com/salomonhotegni/MOREL