Metraipolis › archive › dc_4f3abed67948
arXiv 2610.13363: Adversarial Attacks Reveal Divergent Deception Competence in Humans and Generative Language Models
- Source
- Metraipolis archive
- Original
- https://arxiv.org/abs/2610.13363
- License (as archived)
- CC-BY-4.0
- Archived
- 2026-10-13T03:07:50.465Z
- SHA-256 of the archived text
0b1d6770c68a6a8df3133034a1b81aa494f0142589ec748a70af3aaf3c39a095- Stable URL of this page
https://metraipolis.com/documento/dc_4f3abed67948
How to cite
arXiv 2610.13363: Adversarial Attacks Reveal Divergent Deception Competence in Humans and Generative Language Models — Metraipolis archive, https://arxiv.org/abs/2610.13363 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_4f3abed67948 (Metraipolis archive dc_4f3abed67948, sha256 0b1d6770c68a6a8df3133034a1b81aa494f0142589ec748a70af3aaf3c39a095)
BibTeX
@misc{dc4f3abed67948,
title = {arXiv 2610.13363: Adversarial Attacks Reveal Divergent Deception Competence in Humans and Generative Language Models},
howpublished = {Metraipolis archive},
url = {https://arxiv.org/abs/2610.13363},
note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_4f3abed67948; sha256 0b1d6770c68a6a8df3133034a1b81aa494f0142589ec748a70af3aaf3c39a095},
year = {2026}
}Archived text
Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.13363. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine learning models typically outperform humans in deception detection. A threat to machine learning models is their vulnerability to adversarial attacks: subtle yet targeted perturbations of input data that trick a model into misclassification. Yet, this also provides an opportunity: understanding how humans versus machines construct attacks offers new insights into second-order beliefs about deception. In a preregistered experiment (n = 501), we compare the effectiveness, efficiency, and nature of a paraphrasing attack by humans and generative language models on an automated deception classifier. We find that humans were more effective attackers when rewriting truthful statements to be deceptive, while the generative language model was more effective and efficient at making lies sound like truths. Computational text analysis suggests that this is because humans make targeted use of deception cues, while generative language models, instead, apply generic changes that signal truth. The failure to mimic deception is two-sided: while it exposes a blind spot in the machines increasingly used to detect lies, it also means that language models might facilitate successful lying. Articolo: «Adversarial Attacks Reveal Divergent Deception Competence in Humans and Generative Language Models» — Pfründer, Lucca; Loconte, Riccardo; Verschuere, Bruno; Kleinberg, Bennett (2026-10-09), arXiv:2610.13363, categoria cs.CY (informatica e società). Fonte: https://arxiv.org/abs/2610.13363 Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv. Consultato il 2026-10-13T03:07:45Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.