{"ID":2855530,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12117","arxiv_id":"2510.12117","title":"Locket: Robust Feature-Locking Technique for Language Models","abstract":"Chatbot service providers (e.g., OpenAI) rely on tiered subscription plans to generate revenue, offering black-box access to basic models for free users and advanced models to paying subscribers. However, this approach is unprofitable and inflexible. A pay-to-unlock scheme for premium features (e.g., math, coding) offers a more sustainable alternative. Enabling such a scheme requires a feature-locking technique (FLoTE) that is (i) effective in refusing locked features, (ii) utility-preserving for unlocked features, (iii) robust against evasion or unauthorized credential sharing, and (iv) scalable to multiple features and clients. Existing FLoTEs (e.g., password-locked models) fail to meet these criteria. To fill this gap, we present Locket, the first robust and scalable FLoTE to enable pay-to-unlock schemes. We develop a framework for adversarial training and merging of feature-locking adapters, which enables Locket to selectively disable specific features of a model. Evaluation shows that Locket is effective ($100$% refusal rate), utility-preserving ($\\leq 7$% utility degradation), robust ($\\leq 5$% attack success rate), and scalable to multiple features and clients.","short_abstract":"Chatbot service providers (e.g., OpenAI) rely on tiered subscription plans to generate revenue, offering black-box access to basic models for free users and advanced models to paying subscribers. However, this approach is unprofitable and inflexible. A pay-to-unlock scheme for premium features (e.g., math, coding) offe...","url_abs":"https://arxiv.org/abs/2510.12117","url_pdf":"https://arxiv.org/pdf/2510.12117v3","authors":"[\"Lipeng He\",\"Vasisht Duddu\",\"N. Asokan\"]","published":"2025-10-14T03:35:59Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}