VulnerabilityPublished 24 Sep 2025

CVE-2025-23273: NVIDIA CUDA Toolkit · Divide By Zero

Affects NVIDIA CUDA ToolkitSource CVE Database V5

Not known to be exploited · CVSS 2.5 Low : upgrade to 13.0 when convenient.

Data as of 26 Oct 2026, 14:05 UTC

CVSS 3.1 base score

2.5Low

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.1% chance of exploitation in 30 days – higher than 2% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 13.0

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

Attack Vector: Local
Attack Complexity: High
Privileges Required: Low
User Interaction: None
Scope: Unchanged
Confidentiality: None
Integrity: None
Availability: Low

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Local: The vulnerable component is not bound to the network stack and the attacker’s path is via read/write/execute capabilities. Either: the attacker exploits the vulnerability by accessing the target system locally (e.g., keyboard, console), or remotely (e.g., SSH); or the attacker relies on User Interaction by another person to perform actions required to exploit the vulnerability (e.g., tricking a legitimate user into opening a malicious document).
Attack Complexity: High: A successful attack depends on conditions beyond the attacker's control. That is, a successful attack cannot be accomplished at will, but requires the attacker to invest in some measurable amount of effort in preparation or execution against the vulnerable component before a successful attack can be expected. For example, a successful attack may require an attacker to: gather knowledge about the environment in which the vulnerable target/component exists; prepare the target environment to improve exploit reliability; or inject themselves into the logical network path between the target and the resource requested by the victim in order to read and/or modify network communications (e.g., a man in the middle attack).
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: None: There is no loss of confidentiality within the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the impacted component are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 24 Sep 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade NVIDIA CUDA Toolkit to 13.0.

Affected software

Product	Affected	Fixed in
NVIDIA NVIDIA CUDA Toolkit	Affected <13.0	Fixed in 13.0

AI-suggested

European organizations should implement the following specific mitigation measures: 1) Upgrade to NVIDIA CUDA Toolkit version 13.0 or later as soon as it becomes available, as this version addresses the vulnerability. 2) Restrict local user privileges strictly to minimize the number of users who can execute or submit JPEG files to GPU-accelerated applications using nvJPEG. 3) Implement application-level input validation and sanitization for JPEG files before processing to detect and block malformed or suspicious images that could trigger the divide by zero error. 4) Monitor GPU-accelerated application logs and system stability metrics for signs of crashes or hangs related to image processing. 5) Employ endpoint security solutions that can detect anomalous local user behavior or attempts to exploit local vulnerabilities. 6) In multi-user environments, consider isolating GPU workloads per user or containerizing GPU applications to limit the blast radius of potential DoS attacks. 7) Maintain up-to-date backups and recovery procedures to minimize operational impact in case of service disruption.

Description

NVIDIA CUDA Toolkit for all platforms contains a vulnerability in nvJPEG where a local authenticated user may cause a divide by zero error by submitting a specially crafted JPEG file. A successful exploit of this vulnerability may lead to denial of service.

Impact

For European organizations utilizing NVIDIA CUDA Toolkit in their computing environments—particularly those involved in high-performance computing, AI research, scientific simulations, or image processing workflows—this vulnerability poses a risk of local denial of service. While the impact is limited to availability and does not compromise data confidentiality or integrity, disruption of critical GPU-accelerated workloads could affect operational continuity. Organizations relying on automated image processing pipelines or GPU-accelerated applications that handle JPEG files may experience unexpected crashes or service interruptions if an attacker with local access submits malicious JPEG files. This could lead to downtime, loss of productivity, and potential cascading effects in tightly integrated computational environments. However, the requirement for local authentication and the high complexity of exploitation reduce the likelihood of widespread impact. Nonetheless, environments with shared access or multi-user systems where users have local accounts could be more vulnerable to exploitation attempts.

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 24 Sep 2025, 13:29 UTC

WeaknessesCWE-369

Technical details

References

Community reviews

Related threats