Описание
Уязвимость класса MultiModalHasher библиотеки для работы с большими языковыми моделями (LLM) vLLM связана с неправильной проверкой согласованности во входных данных. Эксплуатация уязвимости может позволить нарушителю, действующему удаленно, раскрыть защищаемую информацию
Вендор
Наименование ПО
Версия ПО
Тип ПО
Операционные системы и аппаратные платформы
Уровень опасности уязвимости
Возможные меры по устранению уязвимости
Статус уязвимости
Наличие эксплойта
Информация об устранении
Идентификаторы других систем описаний уязвимостей
- CVE
EPSS
7.3 High
CVSS3
7.5 High
CVSS2
Связанные уязвимости
vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0.
vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0.
vLLM is an inference and serving engine for large language models (LLM ...
vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
EPSS
7.3 High
CVSS3
7.5 High
CVSS2