Attacking Few-Shot Classifiers with Adversarial Support Poisoning
This paper examines the robustness of deployed few-shot meta-learning systems when they are fed an imperceptibly perturbed few-shot dataset, showing that the resulting predictions on test inputs can become worse than chance. This is achieved by developing a novel attack, Adversarial Support Poisoning or ASP, which crafts a poisoned set of examples. When even a small subset of malicious data points is inserted into the support set of a meta-learner, accuracy is significantly reduced. We evaluate the new attack on a variety of few-shot classification algorithms and scenarios, and propose a form of adversarial training that significantly improves robustness against both poisoning and evasion attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningSimilar Papers 제목 키워드 기반
Attacking Few-Shot Classifiers with Adversarial Support Sets
Few-shot learning systems, especially those based on meta-learning, have recently made significant advances, and are now being considered for real world problems in healthcare, personalization, and science. In this paper…
Few-Shot LearningGeneral ClassificationMeta-LearningTowards 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…
Poisoning Attacks on Fair Machine Learning
Both fair machine learning and adversarial learning have been extensively studied. However, attacking fair machine learning models has received less attention. In this paper, we present a framework that seeks to effectiv…
BIG-bench Machine LearningFairnessAdversarial Examples Make Strong Poisons
The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for att…
Data PoisoningTowards Poisoning Fair Representations
Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female. Recently, fair representation learning (FRL) trained by deep neural networks has demonstrated …
Bilevel OptimizationData PoisoningFairnessRepresentation Learning