Service interruption via shape-tensor size underflow
Published Aug 6, 2025 · Updated Aug 6, 2025
Integer underflow in NVIDIA Triton Inference Server before 25.05 allows remote authenticated users to interrupt service via inference input. TensorRT backend ShapeTensor::SetDataFromBuffer subtracts datatype_size from size_ and passes the wrapped result to memcpy without rejecting undersized buffers. Exploitation requires high privileges, a specific model configuration, and a matching input; NVIDIA has not disclosed whether interruption is a crash, hang, or other failure mode.
Summary
What happened
Integer underflow in NVIDIA Triton Inference Server before 25.05 allows remote authenticated users to interrupt service via inference input. TensorRT backend ShapeTensor::SetDataFromBuffer subtracts datatype_size from size_ and passes the wrapped result to memcpy without rejecting undersized buffers. Exploitation requires high privileges, a specific model configuration, and a matching input; NVIDIA has not disclosed whether interruption is a crash, hang, or other failure mode.
The record
- CVE
- CVE-2025-23335
- Published
- Aug 6, 2025
- Updated
- Aug 6, 2025
- Vendor
- DPDK Project
- Product
- Triton Inference Server
- Classifications
- CWE-191, T1499.004
- Attack vector
- network
- Privileges
- admin
Timeline
How it unfolded
- Aug 6, 2025CVE publishedPublication date reported by the CVE source.
- Aug 6, 2025Record 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.
- Affected versionversion=All versions prior to 25.05
What conditions does exploitation require?
What is affected?
Published CVSS scores
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.
Weakness, pattern, technique
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