AI Models Can Provably Hide Arbitrary Capabilities

[Submitted on ] Title: AI Models Can Provably Hide Arbitrary Capabilities Authors: Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas, Christian Schroeder de Witt View a PDF of the paper titled AI Models Can Provably Hide Arbitrary Capabilities, 3 other authors View PDF HTML (experimental) Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions , decrypting and executing them only upon receiving a secret trigger. Using digital lockers, these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights, extending prior work from hiding fixed strings to arbitrary computations. We implement our proof of concept constructions in PyTorch and evaluate elicitation through fine-tuning, weight noising, gradient-based trigger search, and latent adversarial training on a small chemical reaction prediction task - a proxy for CBRN-relevant capabilities. Our results demonstrate resistance to these methods and, together with our cryptographic guarantees, reveal a limit of elicitation-based capability audits. We release our models to support the improvement of defenses. Accepted at NeurIPS 2026 Subjects: Machine Learning (cs. LG); Cryptography and Security (cs. CR) Cite as: arXiv:2610.13928 [cs. LG]   (or arXiv:2610.13928v1 [cs. LG] for this version)   https://doi. org/10.48550/arXiv.2610.13928 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Andis Draguns [view email] [v1] Fri, :06 UTC (878 KB) Full-text links: Access Paper: View a PDF of the paper titled AI Models Can Provably Hide Arbitrary Capabilities, 3 other authors View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs. LG < prev   |   next > new | recent | 2026-10 Change to browse by: cs cs. CR References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... 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?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) 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?