Preprint
Aug 2026
AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations
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...
Rachel Poonsiriwong, Chayapatr Archiwaranguprok, Constanze Albrecht et al.
· 0 citations