Rebuild and Ensemble: Exploring Defense Against Text Adversaries

03/27/2022
by   Linyang Li, et al.
0

Adversarial attacks can mislead strong neural models; as such, in NLP tasks, substitution-based attacks are difficult to defend. Current defense methods usually assume that the substitution candidates are accessible, which cannot be widely applied against adversarial attacks unless knowing the mechanism of the attacks. In this paper, we propose a Rebuild and Ensemble Framework to defend against adversarial attacks in texts without knowing the candidates. We propose a rebuild mechanism to train a robust model and ensemble the rebuilt texts during inference to achieve good adversarial defense results. Experiments show that our method can improve accuracy under the current strong attack methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/01/2020

Defense of Word-level Adversarial Attacks via Random Substitution Encoding

The adversarial attacks against deep neural networks on computer version...
research
05/08/2021

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]

Recently, few certified defense methods have been developed to provably ...
research
06/05/2021

Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustness

In this paper, we propose a framework of filter-based ensemble of deep n...
research
06/08/2022

Adversarial Text Normalization

Text-based adversarial attacks are becoming more commonplace and accessi...
research
10/06/2022

Dynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks

Adversarial attacks are considered the intrinsic vulnerability of CNNs. ...
research
05/18/2023

Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend

Adversarial attack is commonly regarded as a huge threat to neural netwo...
research
04/14/2023

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

While having achieved great success in rich real-life applications, deep...

Please sign up or login with your details

Forgot password? Click here to reset