CVE-2024-12070: A Denial of Service (DoS) vulnerability exists in the file upload feature of haotian-liu/llava, specifically i

This week

HIGH 7.5REMOTEDOWNGRADE

CVE-2024-12070 is a high-severity flaw (CVSS 7.5) affecting large language and vision assistant. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.

A Denial of Service (DoS) vulnerability exists in the file upload feature of haotian-liu/llava, specifically in Release v1.2.0 (LLaVA-1.6). The vulnerability is due to improper handling of form-data with a large filename in the file upload request. By sending a payload with an excessively large filename, the server becomes overwhelmed and unresponsive, leading to unavailability for legitimate users. This issue can be exploited without authenticat

Why this priority

High severity
Public exploit reference
Remotely exploitable, no login, no user action

No fix is published yet: follow the downgrade or mitigation steps.

Risk facts

CVSS score	7.5 (High)
Attack vector	Network (remote)
Attack complexity	Low
Privileges needed	None
User interaction	None
EPSS exploit chance	0.9% (top 41%)
CISA exploited list	No
Weakness	CWE-400
Published	2025-03-20
Last modified	2026-06-17

Publisher (CNA): huntr.dev · Vendor: hliu

Last updated 2026-06-17 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score

Am I affected?

Timeline

2025-03-20 10:15 UTCPublished CVE record published
2026-06-17 06:58 UTCUpdated Record last modified

hliu large language and vision assistant DOWNGRADE

Affected: 1.2.0

Fixed in: no fixed release known

Safe to downgrade to: a release before 1.2.0

1. Check installed version

apt-cache policy large-language-and-vision-assistant || rpm -q large-language-and-vision-assistant || large-language-and-vision-assistant --version

2. No fixed release: DOWNGRADE to a release before 1.2.0 (Debian / Ubuntu)

apt-cache madison large-language-and-vision-assistant sudo apt install large-language-and-vision-assistant=<VERSION_BEFORE_1.2.0> sudo apt-mark hold large-language-and-vision-assistant

2. No fixed release: DOWNGRADE (RHEL / Amazon Linux / Fedora)

dnf --showduplicates list large-language-and-vision-assistant sudo dnf downgrade large-language-and-vision-assistant-<VERSION_BEFORE_1.2.0> sudo dnf versionlock add large-language-and-vision-assistant

Downgrade risk

Downgrading can break dependent software and may reopen older bugs. Read the distro advisory first and test on a non-production host.

After downgrade

Restart the service, and keep the package held until a fixed release ships.

Verify at the official source NVD · CVE Program · Report a problem with this page
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.

Quick answers

How do I fix CVE-2024-12070?

large language and vision assistant: downgrade or apply the listed mitigation. Exact commands for each OS are on this page.

Is CVE-2024-12070 being exploited?

CVE-2024-12070 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.

What does CVE-2024-12070 affect?

CVE-2024-12070 affects large language and vision assistant. Severity is high (CVSS 7.5). A Denial of Service (DoS) vulnerability exists in the file upload feature of haotian-liu/llava, specifically in Release v1.2.0 (LLaVA-1.6). The vulnerability is due to improper handling of form-data with a large filename in the file upload

How urgent is CVE-2024-12070?

Priority 51/100. High severity; Public exploit reference; Remotely exploitable, no login, no user action

Related CVEs

CVE-2024-9311 MEDIUM 6.1 DOWNGRADE A Cross-Site Request Forgery (CSRF) vulnerability in haotian-liu/llava v1.2.0 (LLaVA-1.6) allows an attacker t
CVE-2024-11449 HIGH 7.5 DOWNGRADE A vulnerability in haotian-liu/llava version 1.2.0 (LLaVA-1.6) allows for Server-Side Request Forgery (SSRF) t

References

← Back to latest CVEs