CVE-2025-54951
📋 TL;DR
Multiple buffer overflow vulnerabilities in ExecuTorch model loading allow attackers to crash the runtime or potentially execute arbitrary code. This affects all systems using ExecuTorch before commit cea9b23aa8ff78aff92829a466da97461cc7930c. The high CVSS score indicates critical severity requiring immediate attention.
💻 Affected Systems
- ExecuTorch
⚠️ Manual Verification Required
This CVE does not have specific version information in our database, so automatic vulnerability detection cannot determine if your system is affected.
Why? The CVE database entry doesn't specify which versions are vulnerable (no version ranges provided by the vendor/NVD).
🔒 Custom verification scripts are available for registered users. Sign up free to download automated test scripts.
- Review the CVE details at NVD
- Check vendor security advisories for your specific version
- Test if the vulnerability is exploitable in your environment
- Consider updating to the latest version as a precaution
⚠️ Risk & Real-World Impact
Worst Case
Remote code execution with full system compromise, allowing attackers to install malware, steal data, or pivot to other systems.
Likely Case
Denial of service through application crashes, potentially disrupting AI/ML inference services and business operations.
If Mitigated
Application crashes without code execution if memory protections like ASLR are effective, but service disruption still occurs.
🎯 Exploit Status
Buffer overflows in model loading are typically exploitable by feeding malicious models. No public exploit code is known at this time.
🛠️ Fix & Mitigation
✅ Official Fix
Patch Version: Commit cea9b23aa8ff78aff92829a466da97461cc7930c and later
Vendor Advisory: https://www.facebook.com/security/advisories/cve-2025-54951
Restart Required: Yes
Instructions:
1. Update ExecuTorch to commit cea9b23aa8ff78aff92829a466da97461cc7930c or later. 2. Rebuild any applications using ExecuTorch. 3. Restart affected services.
🔧 Temporary Workarounds
Model validation and sanitization
allImplement strict validation of ExecuTorch models before loading, rejecting malformed or suspicious models.
Network segmentation
allIsolate systems using ExecuTorch from untrusted networks and implement strict firewall rules.
🧯 If You Can't Patch
- Implement strict input validation for all model loading operations
- Deploy memory protection mechanisms like ASLR and DEP if not already enabled
🔍 How to Verify
Check if Vulnerable:
Check ExecuTorch version/git commit. If before cea9b23aa8ff78aff92829a466da97461cc7930c, you are vulnerable.Check Version:
Check git commit hash or version metadata in your ExecuTorch installationVerify Fix Applied:
Verify ExecuTorch is at commit cea9b23aa8ff78aff92829a466da97461cc7930c or later. Test model loading functionality.📡 Detection & Monitoring
Log Indicators:
- Application crashes during model loading
- Memory access violation errors
- Unexpected process termination
Network Indicators:
- Unexpected model file transfers to ExecuTorch services
- Anomalous network connections to model loading endpoints
SIEM Query:
Process termination events from ExecuTorch applications OR memory violation alerts