Attacking Few-Shot Classifiers with Adversarial Support Poisoning

no code implementations • ICML Workshop AML 2021 • 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.

Meta-Learning

Attacking Few-Shot Classifiers with Adversarial Support Sets

no code implementations • 1 Jan 2021 • 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.

Few-Shot Learning General Classification