# Domain-Independent Deception: Definition, Taxonomy and the Linguistic Cues Debate

arXiv: https://arxiv.org/abs/2207.01738 · HTML: https://mlsanity.com/paper/2207.01738/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2022.

## Built on by (most cited first, 2 of 2)

- [The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind](https://mlsanity.com/paper/2509.20393/) (2025)
- [A Roadmap for Multilingual, Multimodal Domain Independent Deception Detection](https://mlsanity.com/paper/2405.03920/) (2024)

## Abstract (arXiv)

Internet-based economies and societies are drowning in deceptive attacks. These attacks take many forms, such as fake news, phishing, and job scams, which we call "domains of deception." Machine-learning and natural-language-processing researchers have been attempting to ameliorate this precarious situation by designing domain-specific detectors. Only a few recent works have considered domain-independent deception. We collect these disparate threads of research and investigate domain-independent deception along four dimensions. First, we provide a new computational definition of deception and formalize it using probability theory. Second, we break down deception into a new taxonomy. Third, we analyze the debate on linguistic cues for deception and supply guidelines for systematic reviews. Fourth, we provide some evidence and some suggestions for domain-independent deception detection.