SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.13339 · 2020

A Context Aware Approach for Generating Natural Language Attacks

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

We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment tasks. Our proposed attack finds candidate words by considering the information of both the original word and its surrounding context. It jointly leverages masked language modelling and next sentence prediction for context understanding. In comparison to attacks proposed in prior literature, we are able to generate high quality adversarial examples that do significantly better both in terms of success rate and word perturbation percentage.

For agents

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

get_harvested_code_for_paper("2012.13339")
get_code_for_paper("2012.13339")
have("2012.13339")

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

curl https://syntology.ai/api/ran/2012.13339.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.13339.svg)](https://syntology.ai/paper/2012.13339)

Connect an agent — have() is free.