Описание
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.
Ссылки
- Patch
- Issue TrackingVendor Advisory
- Vendor Advisory
Уязвимые конфигурации
EPSS
2.6 Low
CVSS3
Дефекты
Связанные уязвимости
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.
vLLM is an inference and serving engine for large language models (LLM ...
Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching
Уязвимость механизма PageAttention библиотеки для работы с большими языковыми моделями (LLM) vLLM, позволяющая нарушителю раскрыть защищаемую информацию
EPSS
2.6 Low
CVSS3