paper-with-me

홈 › Papers

Attacking Few-Shot Classifiers with Adversarial Support Poisoning

2021-06-18 · ICML Workshop AML 2021 7 · Elre Talea Oldewage, John F Bronskill, Richard E Turner

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Attacking Few-Shot Classifiers with Adversarial Support Sets

2021-01-01 · Elre Talea Oldewage, John F Bronskill, Richard E Turner

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-Learning

Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples

2021-10-24 · Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Ngai-Man Cheung 외

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

2021-10-17 · Minh-Hao Van, Wei Du, Xintao Wu, Aidong Lu

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 LearningFairness

Adversarial Examples Make Strong Poisons

2021-06-21 · NeurIPS 2021 12 · Liam Fowl, Micah Goldblum, Ping-Yeh Chiang, Jonas Geiping 외

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 Poisoning

Towards Poisoning Fair Representations

2023-09-28 · Tianci Liu, Haoyu Wang, Feijie Wu, Hengtong Zhang 외

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