# Efficient Black-Box Adversarial Attacks on Neural Text Detectors

arXiv: https://arxiv.org/abs/2311.01873 · HTML: https://mlsanity.com/paper/2311.01873/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 3 Nov 2023.

## Builds on (most cited first, 12 of 12)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation](https://mlsanity.com/paper/2203.01677/) (2022)
- [Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers](https://mlsanity.com/paper/2203.07983/) (2022)
- [Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series](https://mlsanity.com/paper/2101.05639/) (2021)
- [Mutation-Based Adversarial Attacks on Neural Text Detectors](https://mlsanity.com/paper/2302.05794/) (2023)
- [TextDefense: Adversarial Text Detection based on Word Importance Entropy](https://mlsanity.com/paper/2302.05892/) (2023)

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

- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts](https://mlsanity.com/paper/2409.03291/) (2024)
- [How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study](https://mlsanity.com/paper/2510.13681/) (2025)

## Abstract (arXiv)

Neural text detectors are models trained to detect whether a given text was generated by a language model or written by a human. In this paper, we investigate three simple and resource-efficient strategies (parameter tweaking, prompt engineering, and character-level mutations) to alter texts generated by GPT-3.5 that are unsuspicious or unnoticeable for humans but cause misclassification by neural text detectors. The results show that especially parameter tweaking and character-level mutations are effective strategies.