Commercial large language models are typically deployed as black-box API services, requiring users to trust providers to execute inference correctly and report token usage honestly. We present IMMACULATE, a practical auditing framework that detects economically motivated deviations-such as model substitution, quantization abuse, and token overbilling-without trusted hardware or access to model internals. IMMACULATE selectively audits a small fraction of requests using verifiable computation, achieving strong detection guarantees while amortizing cryptographic overhead. Experiments on dense and MoE models show that IMMACULATE reliably distinguishes benign and malicious executions with under 1% throughput overhead. Our code is published at https://github.com/guo-yanpei/Immaculate.

翻译：商用大语言模型通常以黑盒API服务的形式部署，这要求用户必须信任服务提供商能够正确执行推理并如实报告令牌使用量。本文提出IMMACULATE，一种实用的审计框架，无需可信硬件或模型内部访问权限即可检测经济动机驱动的违规行为——例如模型替换、量化滥用和令牌超额计费。IMMACULATE通过可验证计算对少量请求进行选择性审计，在分摊密码学开销的同时实现强检测保证。在稠密模型与混合专家模型上的实验表明，IMMACULATE能以低于1%的吞吐量开销可靠区分良性执行与恶意执行。我们的代码已发布于https://github.com/guo-yanpei/Immaculate。