Metraipolis › archive › dc_a4028cfd8266

AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations — arXiv:2608.21841

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21841
License (as archived)
CC0-1.0
Archived
2026-10-18T07:39:05.652Z
SHA-256 of the archived text
f381529aafcec533a85c63e7795465bed9704223a6d2255b04eed0b47760b819
Stable URL of this page
https://metraipolis.com/documento/dc_a4028cfd8266

How to cite

AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations — arXiv:2608.21841 — arXiv (en), https://arxiv.org/abs/2608.21841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4028cfd8266 (Metraipolis archive dc_a4028cfd8266, sha256 f381529aafcec533a85c63e7795465bed9704223a6d2255b04eed0b47760b819)
BibTeX
@misc{dca4028cfd8266,
  title = {AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations — arXiv:2608.21841},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21841},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4028cfd8266; sha256 f381529aafcec533a85c63e7795465bed9704223a6d2255b04eed0b47760b819},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI Watchdog, a browser-based agent interface that monitors live conversations, detects five dark-pattern categories, including sycophancy, brand bias, anthropomorphization, sneaking, and harmful generation, and alerts users when they occur. Its open-weight turn-level classifier supports independent deployment and a path toward local inference, preserving user privacy while remaining separate from the conversational AI. We evaluated AI Watchdog in a preregistered, five-condition between-subjects experiment (N = 150) comparing a no-intervention control with four configurations varying nudge timing (prebunking vs. just-in-time) and engagement mode (without vs. with cognitive forcing). Results show that participants rarely flagged manipulative turns across all conditions, and post-task awareness did not differ significantly across groups. However, just-in-time warnings without cognitive forcing were the only intervention to significantly reduce compliance with AI-steered recommendations containing dark patterns, lowering compliance from 71.7% to 53.7%, an 18 percentage-point reduction. Exploratory analyses further showed that lower misinformation susceptibility was associated with greater flagging but not lower compliance, while higher AI trust was associated with greater compliance and lower reported awareness. Together, these findings suggest that explicit recognition of conversational dark patterns and behavioral resistance to AI steering may be distinct outcomes, motivating further investigation of timely, low-friction defensive interfaces.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.21841 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T07:37:52.675Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).