vLLM: Cross-User Data Leak Vulnerability
13Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 5.3epss 0.4%
exploitation probability
0.4%top 68% of all CVEs
observed exploitation
nono source reports it
vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N
Affected products
vllm-project · vllmReferences
https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924https://github.com/vllm-project/vllm/issues/42860https://github.com/vllm-project/vllm/pull/49660https://github.com/vllm-project/vllm/releases/tag/v0.27.0https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5