vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

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.

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L

CWE-1288

vLLM 安全漏洞

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.7.0至0.9.0之前版本存在安全漏洞，该漏洞源于图像哈希方法中仅使用原始像素数据而未包含元数据，可能导致哈希冲突和数据泄露。

N/A

N/A