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

arXiv: https://arxiv.org/abs/2409.18708 · HTML: https://mlsanity.com/paper/2409.18708/

## Key facts

- Cited by 3 papers in the map (data through 7 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems](https://mlsanity.com/paper/1903.11508/) (2019)
- [Shielding Google's language toxicity model against adversarial attacks](https://mlsanity.com/paper/1801.01828/) (2018)
- [On the definition of toxicity in NLP](https://mlsanity.com/paper/2310.02357/) (2023)

## Built on by (most cited first, 3 of 3)

- [The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs](https://mlsanity.com/paper/2501.18626/) (2025)
- [Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models](https://mlsanity.com/paper/2504.01589/) (2025)
- [Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding](https://mlsanity.com/paper/2509.10931/) (2025)

## Abstract (arXiv)

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.