CVE-2025-46722
vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.
Please see our statement on Data Privacy.
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.
Reserved 2025-04-28 | Published 2025-05-29 | Updated 2025-05-29 | Assigner GitHub_MCWE-1288: Improper Validation of Consistency within Input
CWE-1023: Incomplete Comparison with Missing Factors
github.com/...t/vllm/security/advisories/GHSA-c65p-x677-fgj6
github.com/vllm-project/vllm/pull/17378
github.com/...ommit/99404f53c72965b41558aceb1bc2380875f5d848
Support options
