# Adversarial Meta-Learning

arXiv: https://arxiv.org/abs/1806.03316 · HTML: https://mlsanity.com/paper/1806.03316/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2018.

## Built on by (most cited first, 16 of 16)

- [Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition](https://mlsanity.com/paper/2105.03162/) (2021)
- [Few-Shot Adversarial Prompt Learning on Vision-Language Models](https://mlsanity.com/paper/2403.14774/) (2024)
- [On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2102.10454/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [On sensitivity of meta-learning to support data](https://mlsanity.com/paper/2110.13953/) (2021)
- [Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning](https://mlsanity.com/paper/2103.09027/) (2021)
- [Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks](https://mlsanity.com/paper/2106.12900/) (2021)
- [Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners](https://mlsanity.com/paper/2211.12990/) (2022)
- [A Simple Approach to Adversarial Robustness in Few-shot Image Classification](https://mlsanity.com/paper/2204.05432/) (2022)
- [Adversarial Robustification via Text-to-Image Diffusion Models](https://mlsanity.com/paper/2407.18658/) (2024)
- [Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners](https://mlsanity.com/paper/2505.14042/) (2025)
- [Adaptive Adversarial Training for Meta Reinforcement Learning](https://mlsanity.com/paper/2104.13302/) (2021)
- [Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2211.15180/) (2022)
- [Learning Transferable Adversarial Robust Representations via Multi-view Consistency](https://mlsanity.com/paper/2210.10485/) (2022)
- [Robust Few-shot Learning Without Using any Adversarial Samples](https://mlsanity.com/paper/2211.01598/) (2022)
- [Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection](https://mlsanity.com/paper/2507.07994/) (2025)

## Abstract (arXiv)

Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages clean and adversarial samples to optimize the initialization of a learning model in an adversarial manner. ADML leads to the following desirable properties: 1) it turns out to be very effective even in the cases with only clean samples; 2) it is robust to adversarial samples, i.e., unlike other meta-learning algorithms, it only leads to a minor performance degradation when there are adversarial samples; 3) it sheds light on tackling the cases with limited and even contaminated samples. It has been shown by extensive experimental results that ADML consistently outperforms three representative meta-learning algorithms in the cases involving adversarial samples, on two widely-used image datasets, MiniImageNet and CIFAR100, in terms of both accuracy and robustness.