Fetching the paper…

Reading the bibliography…

2020

Attacking Neural Text Detectors

Wolff, Max, Wolff, Stuart

Original
PDF
Post on X

Understand

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.

Attacking Neural Text Detectors · Around

Built on

Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian J. Goodfellow, and Rob Fergus · 2014
Earlier work this paper cites.
Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition
Mahmood Sharif, Sruti Bhagavatula, Lujo Bauer, and Michael K. Reiter · 2016
Earlier work this paper cites.
Synthesizing robust adversarial examples
Anish Athalye, Logan Engstrom, Andrew Ilyas, and Kevin Kwok · 2018
Earlier work this paper cites.

Similar

HotFlip: White-box adversarial examples for text classification
Javid Ebrahimi, Anyi Rao, Daniel Lowd, and Dejing Dou · 2018
Cited alongside, same era.
GLTR: Statistical detection and visualization of generated text
Sebastian Gehrmann, Hendrik Strobelt, and Alexander Rush · 2019
Cited alongside, same era.
Roberta: A robustly optimized BERT pretraining approach
Original
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov · 2019
Cited alongside, same era.

Then

Language models are unsupervised multitask learners
Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever · 2019
Later among the works it cites.
Release strategies and the social impacts of language models, 2019
Irene Solaiman, Miles Brundage, Jack Clark, Amanda Askell, Ariel Herbert-Voss, Jeff Wu, Alec Radford, Gretchen Krueger, Jong Wook Kim, Sarah Kreps, Miles McCain, Alex Newhouse, Jason Blazakis, Kris McGuffie, and Jasmine Wang · 2019
Later among the works it cites.
Defending against neural fake news
Original
Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi · 2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…