paper-with-me

홈 › Papers

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, Yuval Elovici, Alexander Binder

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.

📄 PDF Abstract BibTeX arXiv:2110.12357

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging

2024-11-07 · Rui Luo, Jie Bao, Zhixin Zhou, Chuangyin Dang

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+1

Defensive Few-shot Learning

2019-11-16 · Wenbin Li, Lei Wang, Xingxing Zhang, Lei Qi 외

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 Learning

Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples

2019-08-21 · Marcus Soll, Tobias Hinz, Sven Magg, Stefan Wermter

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+3

Why Blocking Targeted Adversarial Perturbations Impairs the Ability to Learn

2019-07-11 · Ziv Katzir, Yuval Elovici

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…

Blockingvalid

MetaGAN: An Adversarial Approach to Few-Shot Learning

2018-12-01 · NeurIPS 2018 12 · Ruixiang Zhang, Tong Che, Zoubin Ghahramani, Yoshua Bengio 외

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