# Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering

arXiv: https://arxiv.org/abs/2012.06330 · HTML: https://mlsanity.com/paper/2012.06330/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

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

- [Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples](https://mlsanity.com/paper/2110.12357/) (2021)

## Abstract (arXiv)

Few-shot classifiers excel under limited training samples, making them useful in applications with sparsely user-provided labels. Their unique relative prediction setup offers opportunities for novel attacks, such as targeting support sets required to categorise unseen test samples, which are not available in other machine learning setups. In this work, we propose a detection strategy to identify adversarial support sets, aimed at destroying the understanding of a few-shot classifier for a certain class. We achieve this by introducing the concept of self-similarity of a support set and by employing filtering of supports. Our method is attack-agnostic, and we are the first to explore adversarial detection for support sets of few-shot classifiers to the best of our knowledge. Our evaluation of the miniImagenet (MI) and CUB datasets exhibits good attack detection performance despite conceptual simplicity, showing high AUROC scores. We show that self-similarity and filtering for adversarial detection can be paired with other filtering functions, constituting a generalisable concept.