SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.11768 · ICLR · 2020

Attacking Neural Text Detectors

Max Wolff, Stuart Wolff

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

Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these language models. This paper presents two classes of black-box attacks on these detectors, one which randomly replaces characters with homoglyphs, and the other a simple scheme to purposefully misspell words. The homoglyph and misspelling attacks decrease a popular neural text detector's recall on neural text from 97.44% to 0.26% and 22.68%, respectively. Results also indicate that the attacks are transferable to other neural text detectors.

For agents

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

get_harvested_code_for_paper("2002.11768")
get_code_for_paper("2002.11768")
have("2002.11768")

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

curl https://syntology.ai/api/ran/2002.11768.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.11768.svg)](https://syntology.ai/paper/2002.11768)

Connect an agent — have() is free.