Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
Few-shot classifiers have been shown to exhibit promising results in use cases where user-provided labels are scarce. These models are able to learn to predict novel classes simply by training on a non-overlapping set of classes. This can be largely attributed to the differences in their mechanisms as compared to conventional deep networks. However, this also offers new opportunities for novel attackers to induce integrity attacks against such models, which are not present in other machine learning setups. In this work, we aim to close this gap by studying a conceptually simple approach to defend few-shot classifiers against adversarial attacks. More specifically, we propose a simple attack-agnostic detection method, using the concept of self-similarity and filtering, to flag out adversarial support sets which destroy the understanding of a victim classifier for a certain class. Our extended evaluation on the miniImagenet (MI) and CUB datasets exhibit good attack detection performance, across three different few-shot classifiers and across different attack strengths, beating baselines. Our observed results allow our approach to establishing itself as a strong detection method for support set poisoning attacks. We also show that our approach constitutes a generalizable concept, as it can be paired with other filtering functions. Finally, we provide an analysis of our results when we vary two components found in our detection approach.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging
Adversarial attacks pose significant threats to the reliability and safety of deep learning models, especially in critical domains such as medical imaging. This paper introduces a novel framework that integrates conforma…
Adversarial RobustnessConformal PredictionPredictionUncertainty Quantification+1Defensive Few-shot Learning
This paper investigates a new challenging problem called defensive few-shot learning in order to learn a robust few-shot model against adversarial attacks. Simply applying the existing adversarial defense methods to few-…
Adversarial DefenseFew-Shot LearningEvaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples
Adversarial examples are artificially modified input samples which lead to misclassifications, while not being detectable by humans. These adversarial examples are a challenge for many tasks such as image and text classi…
Adversarial TextClassificationGeneral Classificationimage-classification+3Why Blocking Targeted Adversarial Perturbations Impairs the Ability to Learn
Despite their accuracy, neural network-based classifiers are still prone to manipulation through adversarial perturbations. Those perturbations are designed to be misclassified by the neural network, while being perceptu…
BlockingvalidMetaGAN: An Adversarial Approach to Few-Shot Learning
In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems. Most state-of-the-art few-shot classification models can be integrated with MetaGAN in a principled and…
ClassificationFew-Shot Image ClassificationFew-Shot LearningGeneral Classification+2