Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries

03/27/2021
by   Kun-Peng Ning, et al.
20

In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise perturbations. Most existing studies assume a fixed perturbation level for all training examples, which however hardly holds in real tasks. In fact, excessive perturbations may destroy the discriminative content of an example, while deficient perturbations may fail to provide helpful information for improving the robustness. Motivated by this observation, we propose to adaptively adjust the perturbation levels for each example in the training process. Specifically, a novel active learning framework is proposed to allow the model to interactively query the correct perturbation level from human experts. By designing a cost-effective sampling strategy along with a new query type, the robustness can be significantly improved with a few queries. Both theoretical analysis and experimental studies validate the effectiveness of the proposed approach.

READ FULL TEXT

page 2

page 4

research
10/15/2021

RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models

Backdoor attacks, which maliciously control a well-trained model's outpu...
research
06/22/2020

Learning to Generate Noise for Robustness against Multiple Perturbations

Adversarial learning has emerged as one of the successful techniques to ...
research
04/20/2023

Certified Adversarial Robustness Within Multiple Perturbation Bounds

Randomized smoothing (RS) is a well known certified defense against adve...
research
09/22/2021

Exploring Adversarial Examples for Efficient Active Learning in Machine Learning Classifiers

Machine learning researchers have long noticed the phenomenon that the m...
research
07/24/2023

Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs

As deep learning models continue to advance and are increasingly utilize...
research
06/19/2018

Maximally Invariant Data Perturbation as Explanation

While several feature scoring methods are proposed to explain the output...
research
04/09/2020

Natural Perturbation for Robust Question Answering

While recent models have achieved human-level scores on many NLP dataset...

Please sign up or login with your details

Forgot password? Click here to reset