让大模型按功能收费，解锁特定能力需付费
Locket: Robust Feature-Locking Technique for Language Models
- 用对抗训练和适配器合并实现功能精准锁闭
- 锁功能成功率100%，未解锁功能损失≤7%
- 防破解能力强，适合多用户多功能场景
聊天机器人服务商依赖分级订阅盈利，对免费用户提供封闭式基础模型，而付费用户可访问高级模型。但此模式不可持续且缺乏灵活性。采用按功能付费解锁（如数学、编程）更具可持续性。这需要一种特征锁技术（FLoTE），满足四点：(i) 有效阻止锁定功能，(ii) 对未锁定功能保持可用性，(iii) 抗规避与非法共享，(iv) 支持多功能与多客户端扩展。现有方案（如密码锁模型）无法满足。为此，我们提出Locket，首个稳健且可扩展的FLoTE，支持按功能付费。通过构建对抗训练与适配器融合框架，实现模型特定功能的可选禁用。评估显示，Locket在拒绝率（100%）、性能损失（≤7%）、抗攻击成功率（≤5%）及多任务多用户扩展方面表现优异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。