CVE-2026-47475

Inference interruption via unvalidated logit bias

Published Jul 14, 2026 · Updated Jul 14, 2026

Reachable assertion in NVIDIA TensorRT-LLM 1.3.0rc15 and earlier allows local users to interrupt inference via crafted logit bias. The OpenAI-compatible chat, completion, and chat_harmony paths passed logit_bias token IDs and values into sampling without complete bounds and finiteness validation. Local access to the inference API is required, and the resulting sampler-thread assertion interrupts availability without reported data exposure or modification.

CVSS severity6.2
Medium
EPSS probability0.16%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Reachable assertion in NVIDIA TensorRT-LLM 1.3.0rc15 and earlier allows local users to interrupt inference via crafted logit bias. The OpenAI-compatible chat, completion, and chat_harmony paths passed logit_bias token IDs and values into sampling without complete bounds and finiteness validation. Local access to the inference API is required, and the resulting sampler-thread assertion interrupts availability without reported data exposure or modification.

The record

CVE
CVE-2026-47475
Published
Jul 14, 2026
Updated
Jul 14, 2026
Vendor
DPDK Project
Product
TensorRT-LLM
Classifications
CWE-617, T1499.004
Attack vector
local
Privileges
unauthenticated

Timeline

How it unfolded

  1. Jul 14, 2026CVE publishedPublication date reported by the CVE source.
  2. Jul 14, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0.0 <=v1.3.0 rc15

What conditions does exploitation require?

Attack vectorlocal
Required privilegesunauthenticated

What is affected?

DPDK Project · TensorRT-LLMversion=0.0 <=v1.3.0 rc15

Published CVSS scores

6.2NVIDIACVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectorlocal
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-617Reachable Assertion
T1499.004Application or System Exploitation

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo