翻訳待ち：Model Hypnosis: Strong control of AI via additive subliminal effects

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。

--> [Submitted on 17 Aug 2026] Title:Model Hypnosis: Strong control of AI via additive subliminal effects View a PDF of the paper titled Model Hypnosis: Strong control of AI via additive subliminal effects, by Enric Boix-Adsera and Benedict Tessler View PDF HTML (experimental) Abstract:We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be systematically combined to strongly control model behavior. Model hypnosis occurs across model families and scales, including in frontier reasoning models, and hypnotic prompts can transfer between models. Because the model is controlled by inconspicuous textual choices, such as paraphrases and typos, model hypnosis presents new challenges and avenues for AI safety, and is a major hurdle for AI interpretability. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2608.16834 [cs.CL] (or arXiv:2608.16834v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.16834 arXiv-issued DOI via DataCite (pending registration) Submission history From: Enric Boix-Adserà [view email] [v1] Mon, 17 Aug 2026 17:20:10 UTC (4,688 KB) Full-text links: Access Paper: View a PDF of the paper titled Model Hypnosis: Strong control of AI via additive subliminal effects, by Enric Boix-Adsera and Benedict Tessler View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-08 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)