vllm
Affected
- introduced
0.7.0, fixed0.9.0(ecosystem)
Fixed versions
0.9.0
Fix
- Fixed version
0.9.0pip install --upgrade vllm==0.9.0
Advisory
Also known as: CVE-2025-46722, PYSEC-2025-43
vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
Summary
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.
Details
vllm/multimodal/hasher.pyMultiModalHasher.serialize_itemhttps://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35
Image.Image instances, only obj.tobytes() is used for hashing.obj.tobytes() does not include the image’s width, height, or mode metadata.Recommendation
In the serialize_item method, serialization of `Image.Image` objects should include not only pixel data, but also all critical metadata—such as dimensions (size), color mode (mode), format, and especially the info dictionary. The info dictionary is particularly important in palette-based images (e.g., mode 'P'), where the palette itself is stored in info. Ignoring info can result in hash collisions between visually distinct images with the same pixel bytes but different palettes or metadata. This can lead to incorrect cache hits or even data leakage.
Summary:
Serializing only the raw pixel data is insecure. Always include all image metadata (size, mode, format, info) in the hash calculation to prevent collisions, especially in cases like palette-based images.
Impact for other modalities
For the influence of other modalities, since the video modality is transformed into a multi-dimensional array containing the length, width, time, etc. of the video, the same problem exists due to the incorrect sequence of numpy as well.
For audio, since the momo function is not enabled in librosa.load, the loaded audio is automatically encoded into single channels by librosa and returns a one-dimensional array of numpy, thus keeping the structure of numpy fixed and not affected by this issue.
Fixes
Medium Basis: The source's own band: MODERATE
0.7.0, fixed 0.9.0 (ecosystem)0.9.0
0.9.0pip install --upgrade vllm==0.9.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0