SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.18708 · 2024

Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems

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 introduce a novel class of adversarial attacks on toxicity detection models that exploit language models' failure to interpret spatially structured text in the form of ASCII art. To evaluate the effectiveness of these attacks, we propose ToxASCII, a benchmark designed to assess the robustness of toxicity detection systems against visually obfuscated inputs. Our attacks achieve a perfect Attack Success Rate (ASR) across a diverse set of state-of-the-art large language models and dedicated moderation tools, revealing a significant vulnerability in current text-only moderation systems.

For agents

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

get_harvested_code_for_paper("2409.18708")
get_code_for_paper("2409.18708")
have("2409.18708")

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

curl https://syntology.ai/api/ran/2409.18708.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.18708.svg)](https://syntology.ai/paper/2409.18708)

Connect an agent — have() is free.