{"id":63917,"date":"2025-05-29T21:31:53","date_gmt":"2025-05-29T18:01:53","guid":{"rendered":"https:\/\/afaghhosting.net\/blog\/cve-2025-46722-vllm-image-hash-collision-vulnerability\/"},"modified":"2025-05-29T21:31:53","modified_gmt":"2025-05-29T18:01:53","slug":"cve-2025-46722-vllm-image-hash-collision-vulnerability","status":"publish","type":"post","link":"https:\/\/afaghhosting.net\/blog\/cve-2025-46722-vllm-image-hash-collision-vulnerability\/","title":{"rendered":"CVE-2025-46722 &#8211; VLLM Image Hash Collision Vulnerability"},"content":{"rendered":"<p><strong>CVE ID : <\/strong>CVE-2025-46722<br \/>\n<br \/>\n<strong>Published : <\/strong> May 29, 2025, 5:15 p.m. | 39\u00a0minutes ago<br \/>\n<br \/>\n<strong>Description : <\/strong>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\u2019s shape (width, height, mode). As a result, two images of different sizes (e.g., 30&#215;100 and 100&#215;30) 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.<br \/>\n<br \/>\n<strong>Severity:<\/strong> 4.2 | MEDIUM<br \/>\n<br \/>\nVisit the link for more details, such as CVSS details, affected products, timeline, and more&#8230;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>CVE ID : CVE-2025-46722 Published : May 29, 2025, 5:15 p.m. | 39\u00a0minutes ago Description : 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. &hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[26],"tags":[],"class_list":["post-63917","post","type-post","status-publish","format-standard","hentry","category-vulnerability"],"_links":{"self":[{"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/posts\/63917","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/comments?post=63917"}],"version-history":[{"count":0,"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/posts\/63917\/revisions"}],"wp:attachment":[{"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/media?parent=63917"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/categories?post=63917"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/afaghhosting.net\/blog\/wp-json\/wp\/v2\/tags?post=63917"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}