Process crash via zero-batch GPU SVD assertion
Published Sep 16, 2022 · Updated Apr 23, 2025
Reachable assertion in Google TensorFlow before 2.7.2, 2.8.0, and 2.9.0 allows attackers to crash GPU-backed processes. SvdOpGpu submits a zero-batch SVD with work_element_count equal to zero instead of returning after allocating empty outputs, triggering a CHECK failure. Exploitation requires attacker-controlled input to reach tf.linalg.matrix_rank in a process using the GPU kernel, and the failure terminates that process.
Summary
What happened
Reachable assertion in Google TensorFlow before 2.7.2, 2.8.0, and 2.9.0 allows attackers to crash GPU-backed processes. SvdOpGpu submits a zero-batch SVD with work_element_count equal to zero instead of returning after allocating empty outputs, triggering a CHECK failure. Exploitation requires attacker-controlled input to reach tf.linalg.matrix_rank in a process using the GPU kernel, and the failure terminates that process.
The record
- CVE
- CVE-2022-35988
- Published
- Sep 16, 2022
- Updated
- Apr 23, 2025
- Vendor
- Product
- TensorFlow
- Classifications
- CWE-617, T1499.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 16, 2022CVE publishedPublication date reported by the CVE source.
- Apr 23, 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=< 2.7.2
- Affected versionversion=>= 2.8.0, < 2.8.1
- Affected versionversion=>= 2.9.0, < 2.9.1
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
- Empty matrix_rank input reproducerproof of concept · demonstrated
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