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 8 of 47
Current
SeverityCVECVSS
MEDIUMCVE-2021-376885.5
MEDIUMCVE-2021-376895.5
HIGHCVE-2021-376637.8
HIGHCVE-2021-376657.8
MEDIUMCVE-2021-376685.5
MEDIUMCVE-2021-376695.5
MEDIUMCVE-2021-376735.5
MEDIUMCVE-2021-376775.5
HIGHCVE-2021-376827.1
MEDIUMCVE-2021-376835.5
MEDIUMCVE-2021-376845.5
MEDIUMCVE-2021-376855.5
MEDIUMCVE-2021-376875.5
MEDIUMCVE-2021-376915.5
MEDIUMCVE-2021-411965.5
MEDIUMCVE-2021-411975.5
MEDIUMCVE-2021-411985.5
MEDIUMCVE-2021-411995.5
HIGHCVE-2021-412017.8
MEDIUMCVE-2021-412045.5

Page 8 of 47