Unauthenticated server crash via batch-size integer overflow
Published Aug 6, 2025 · Updated Aug 6, 2025
Integer overflow in NVIDIA Triton Inference Server before 25.05 allows remote attackers to crash the server with an invalid request. InferenceRequest::Normalize casts the unsigned batch_size_ value to a signed int when comparing it with the model's maximum batch size, allowing an oversized value to bypass validation. Unauthenticated network access to an inference endpoint is sufficient; successful exploitation terminates the server process with a segmentation fault.
Summary
What happened
Integer overflow in NVIDIA Triton Inference Server before 25.05 allows remote attackers to crash the server with an invalid request. InferenceRequest::Normalize casts the unsigned batch_size_ value to a signed int when comparing it with the model's maximum batch size, allowing an oversized value to bypass validation. Unauthenticated network access to an inference endpoint is sufficient; successful exploitation terminates the server process with a segmentation fault.
The record
- CVE
- CVE-2025-23324
- Published
- Aug 6, 2025
- Updated
- Aug 6, 2025
- Vendor
- DPDK Project
- Product
- Triton Inference Server
- Classifications
- CWE-190, T1499.004
- Attack vector
- network
- Privileges
- unauthenticated
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