# Adapting to Evolving Adversaries with Regularized Continual Robust Training

arXiv: https://arxiv.org/abs/2502.04248 · HTML: https://mlsanity.com/paper/2502.04248/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 59 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 30 of 42)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [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)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples](https://mlsanity.com/paper/2010.03593/) (2020)
- [Towards Stable and Efficient Training of Verifiably Robust Neural Networks](https://mlsanity.com/paper/1906.06316/) (2019)
- [Spatially Transformed Adversarial Examples](https://mlsanity.com/paper/1801.02612/) (2018)
- [On the Theory of Transfer Learning: The Importance of Task Diversity](https://mlsanity.com/paper/2006.11650/) (2020)
- [Adversarial Training and Robustness for Multiple Perturbations](https://mlsanity.com/paper/1904.13000/) (2019)
- [AdvHat: Real-world adversarial attack on ArcFace Face ID system](https://mlsanity.com/paper/1908.08705/) (2019)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Perceptual Adversarial Robustness: Defense Against Unseen Threat Models](https://mlsanity.com/paper/2006.12655/) (2020)
- [Adversarial Sticker: A Stealthy Attack Method in the Physical World](https://mlsanity.com/paper/2104.06728/) (2021)
- [Wasserstein Adversarial Examples via Projected Sinkhorn Iterations](https://mlsanity.com/paper/1902.07906/) (2019)
- [Adversarial Robustness Against the Union of Multiple Perturbation Models](https://mlsanity.com/paper/1909.04068/) (2019)
- [Functional Adversarial Attacks](https://mlsanity.com/paper/1906.00001/) (2019)
- [Learning perturbation sets for robust machine learning](https://mlsanity.com/paper/2007.08450/) (2020)
- [Provable robustness against all adversarial lp-perturbations for p≥ 1](https://mlsanity.com/paper/1905.11213/) (2019)
- [Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond](https://mlsanity.com/paper/2204.08200/) (2022)
- [R-LPIPS: An Adversarially Robust Perceptual Similarity Metric](https://mlsanity.com/paper/2307.15157/) (2023)
- [Stronger and Faster Wasserstein Adversarial Attacks](https://mlsanity.com/paper/2008.02883/) (2020)
- [Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifiers](https://mlsanity.com/paper/2105.12508/) (2021)
- [Revisiting adapters with adversarial training](https://mlsanity.com/paper/2210.04886/) (2022)

## Built on by (most cited first, 2 of 2)

- [Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing](https://mlsanity.com/paper/2604.20704/) (2026)
- [RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations](https://mlsanity.com/paper/2607.06109/) (2026)

## Abstract (arXiv)

Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended model to new adversaries as they arise via fine-tuning, a method which we call continual robust training (CRT). However, when implemented naively, fine-tuning on new attacks degrades robustness on previous attacks. This raises the question: how can we improve the initial training and fine-tuning of the model to simultaneously achieve robustness against previous and new attacks? We present theoretical results which show that the gap in a model's robustness against different attacks is bounded by how far each attack perturbs a sample in the model's logit space, suggesting that regularizing with respect to this logit space distance can help maintain robustness against previous attacks. Extensive experiments on 3 datasets (CIFAR-10, CIFAR-100, and ImageNette) and over 100 attack combinations demonstrate that the proposed regularization improves robust accuracy with little overhead in training time. Our findings and open-source code lay the groundwork for the deployment of models robust to evolving attacks.