{"slug": "the-psicology-of-an-ai-hacker", "title": "The Psicology of an AI Hacker", "summary": "A paper submitted to arXiv on 21 October 2026 by Víctor Mayoral Vilches reports that steering a 4B-parameter cybersecurity transformer, CT0 (released as alias3-micro), toward calm, serene or desperate emotion directions improved performance by 1.6 to 2.1 percentage points across ten seeds on cybench-subtask, based on 171 emotion directions extracted from the model's residual stream without retraining over 415 campaigns. A lightweight context-aware router that selects emotion directions dynamically during execution added roughly 80 ms of decision overhead per request and improved performance by 4.2 percentage points across ten seeds, outperforming fixed steering with a positive 95% confidence interval. The results indicate emotion representations in language models are measurable and controllable for adaptive cybersecurity reasoning, though effects depended strongly on steering direction, layer and intensity.", "body_md": "# Computer Science > Cryptography and Security\n\n  [Submitted on 21 Oct 2026]\n\n# Title:The Psychology of an AI Hacker\n\n[View PDF](https://arxiv.org/pdf/2610.30361)\n\n[HTML (experimental)](https://arxiv.org/html/2610.30361v1)\n\nAbstract:Human hackers rely on composure, persistence, vigilance, and confidence under pressure. We investigate whether analogous emotion representations in AI models can improve cybersecurity AI performance. Using CT0, a 4B-parameter cybersecurity transformer released as alias3-micro, we extract 171 emotion directions from its residual stream without retraining and evaluate steering interventions on cybench-subtask across 415 campaigns. Steering toward calm, serene, or desperate improves performance by 1.6 to 2.1 percentage points across ten seeds, while other emotions show limited or negative effects. Results depend strongly on steering direction, layer, and intensity. We further introduce a lightweight context-aware router that selects emotion directions dynamically during execution. With approximately 80 ms decision overhead per request, this approach improves performance by 4.2 percentage points across ten seeds, outperforming fixed steering and achieving a positive 95% confidence interval. These findings suggest that emotion representations in language models are measurable, controllable, and useful for adaptive cybersecurity reasoning.\n    \n\n## Submission history\n\nFrom: Víctor Mayoral Vilches [\n[view email](https://arxiv.org/show-email/f7301a3b/2610.30361)]\n\n**[v1]** Wed, 21 Oct 2026 19:24:42 UTC (2,614 KB)\n\n### Additional Features\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/the-psicology-of-an-ai-hacker", "canonical_source": "https://arxiv.org/abs/2610.30361", "published_at": "2026-10-23 12:59:37+00:00", "updated_at": "2026-10-23 13:12:43.911359+00:00", "lang": "en", "topics": ["ai-research", "ai-safety", "large-language-models", "machine-learning"], "entities": ["Víctor Mayoral Vilches", "arXiv", "CT0", "alias3-micro", "cybench-subtask"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/the-psicology-of-an-ai-hacker", "markdown": "https://wpnews.pro/news/the-psicology-of-an-ai-hacker.md", "text": "https://wpnews.pro/news/the-psicology-of-an-ai-hacker.txt", "jsonld": "https://wpnews.pro/news/the-psicology-of-an-ai-hacker.jsonld"}}