A Deep Dive into Adversarial Robustness in Zero-Shot Learning

08/17/2020
by   Mehmet Kerim Yucel, et al.
0

Machine learning (ML) systems have introduced significant advances in various fields, due to the introduction of highly complex models. Despite their success, it has been shown multiple times that machine learning models are prone to imperceptible perturbations that can severely degrade their accuracy. So far, existing studies have primarily focused on models where supervision across all classes were available. In constrast, Zero-shot Learning (ZSL) and Generalized Zero-shot Learning (GZSL) tasks inherently lack supervision across all classes. In this paper, we present a study aimed on evaluating the adversarial robustness of ZSL and GZSL models. We leverage the well-established label embedding model and subject it to a set of established adversarial attacks and defenses across multiple datasets. In addition to creating possibly the first benchmark on adversarial robustness of ZSL models, we also present analyses on important points that require attention for better interpretation of ZSL robustness results. We hope these points, along with the benchmark, will help researchers establish a better understanding what challenges lie ahead and help guide their work.

READ FULL TEXT
research
01/26/2022

How Robust are Discriminatively Trained Zero-Shot Learning Models?

Data shift robustness has been primarily investigated from a fully super...
research
10/23/2022

TAPE: Assessing Few-shot Russian Language Understanding

Recent advances in zero-shot and few-shot learning have shown promise fo...
research
06/15/2019

Uncovering Why Deep Neural Networks Lack Robustness: Representation Metrics that Link to Adversarial Attacks

Neural networks have been shown vulnerable to adversarial samples. Sligh...
research
01/30/2023

Anchor-Based Adversarially Robust Zero-Shot Learning Driven by Language

Deep neural networks are vulnerable to adversarial attacks. We consider ...
research
02/26/2021

Knowledge-aware Zero-Shot Learning: Survey and Perspective

Zero-shot learning (ZSL) which aims at predicting classes that have neve...
research
06/19/2020

Normalization Matters in Zero-Shot Learning

An ability to grasp new concepts from their descriptions is one of the k...
research
04/10/2019

On zero-shot recognition of generic objects

Many recent advances in computer vision are the result of a healthy comp...

Please sign up or login with your details

Forgot password? Click here to reset