AI Component

Inference

Inference servers are the most actively-exploited component of the AI stack because they sit between the model and the public internet and they hold the GPU. The shape of the bugs is mostly web-app classes magnified by the cost of compute: missing auth on /v1 endpoints, SSRF that escapes the sandbox onto the platform's control plane, unsafe deserialization on model-loading paths, and path traversal in artifact-management endpoints. vLLM, Triton, TGI, BentoML, Ray Serve, and Ollama have each shipped multiple high-severity CVEs since 2023; CVE-2024-11041 in vLLM was a notable example combining prompt injection with code execution. Multi-tenant deployments are particularly exposed because a single bug typically crosses tenant boundaries. Defenses: aggressive patching, mandatory auth, network segmentation between inference and control plane, and per-tenant resource quotas to bound abuse.

938
Total CVEs
47
Pages
Page 7 of 47
Current
SeverityCVECVSS
MEDIUMCVE-2021-296185.5
MEDIUMCVE-2021-296195.5
MEDIUMCVE-2021-376405.5
MEDIUMCVE-2021-376425.5
MEDIUMCVE-2021-376535.5
HIGHCVE-2021-376387.8
MEDIUMCVE-2021-376475.5
MEDIUMCVE-2021-376495.5
HIGHCVE-2021-376417.1
HIGHCVE-2021-376567.8
HIGHCVE-2021-376577.8
HIGHCVE-2021-376587.8
HIGHCVE-2021-376597.8
HIGHCVE-2021-376677.8
HIGHCVE-2021-376717.8
MEDIUMCVE-2021-376755.5
HIGHCVE-2021-376767.8
MEDIUMCVE-2021-376805.5
HIGHCVE-2021-376817.8
MEDIUMCVE-2021-376865.5

Page 7 of 47