SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.00446 · 2020

Defense of Word-level Adversarial Attacks via Random Substitution Encoding

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural Language Processing (NLP) tasks have also demonstrated strong power, e.g., fooling a sentiment classification neural network to make wrong decisions. Unfortunately, few previous literatures have discussed the defense of such word-level synonym substitution based attacks since they are hard to be perceived and detected. In this paper, we shed light on this problem and propose a novel defense framework called Random Substitution Encoding (RSE), which introduces a random substitution encoder into the training process of original neural networks. Extensive experiments on text classification tasks demonstrate the effectiveness of our framework on defense of word-level adversarial attacks, under various base and attack models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.00446")
get_code_for_paper("2005.00446")
have("2005.00446")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2005.00446.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2005.00446.svg)](https://syntology.ai/paper/2005.00446)

Connect an agent — have() is free.