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 for the users. 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 enable or 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.

翻译：摘要：聊天机器人服务提供商（如OpenAI）依赖分级订阅计划来创造收入，为免费用户提供基础模型的黑盒访问权限，而付费用户则可使用高级模型。然而，这种方式对用户而言利润较低且缺乏灵活性。针对高级特性（如数学运算、编程能力）的按需付费解锁方案提供了一种更可持续的替代方案。实现此类方案需要一种特性锁定技术（FLoTE），其需满足：（i）有效拒绝锁定特性，（ii）保持解锁特性的实用价值，（iii）抗规避或未授权凭证共享的鲁棒性，以及（iv）可扩展至多特性与多客户端。现有FLoTE（如密码锁定模型）无法满足这些标准。为填补这一空白，我们提出Locket——首个支持按需付费解锁方案的鲁棒且可扩展的FLoTE。我们开发了对抗训练与特性锁定适配器融合框架，使Locket能够选择性启用或禁用模型的特定特性。评估表明，Locket具有有效性（100%拒绝率）、实用性保持（≤7%效用下降）、鲁棒性（≤5%攻击成功率）及对多特性与多客户端的可扩展性。