Vendor
PyTorch vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 8 vulnerabilities in PyTorch: 0 in the last 7 days and 1 in the last 90 days, 0 of them critical and 0 exploited in the wild. The most recent, CVE-2026-65918, was published on 23 July 2026. 1 technology has a page of its own.
- Last 7 days
- 0
- Last 90 days
- 1
- Critical, all time
- 0
- Exploited in the wild
- 0
About PyTorch
PyTorch is an open-source machine learning framework based on the Torch library.
PyTorch technologies
Latest PyTorch vulnerabilities
- CVE-2026-65918: PyTorch torchvision out-of-bounds read in GIF decoderhighCVSS 7.1
- CVE-2025-3001: PyTorch memory corruption in torch.lstm_cellmediumCVSS 5.3EPSS 0.2%
- CVE-2025-3000: PyTorch memory corruption in torch.jit.scriptmediumCVSS 5.3EPSS 0.2%
- CVE-2025-2998: PyTorch memory corruption in pad_packed_sequencemediumCVSS 5.3EPSS 0.2%
- CVE-2025-2999: PyTorch memory corruption in unpack_sequence and pad_packed_sequencemediumCVSS 5.3EPSS 0.2%
- CVE-2025-2953: PyTorch denial of service in torch.mkldnn_max_pool2dlowCVSS 3.3EPSS 0.3%
- CVE-2025-2149: PyTorch improper initialization in Quantized Sigmoid ModulemediumCVSS 4EPSS 0.3%
- CVE-2025-2148: PyTorch memory corruption in profiler Tuple HandlermediumCVSS 5EPSS 0.4%
Most severe PyTorch vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-65918: PyTorch torchvision out-of-bounds read in GIF decoderhighCVSS 7.1
- CVE-2025-3001: PyTorch memory corruption in torch.lstm_cellmediumCVSS 5.3EPSS 0.2%
- CVE-2025-3000: PyTorch memory corruption in torch.jit.scriptmediumCVSS 5.3EPSS 0.2%
- CVE-2025-2998: PyTorch memory corruption in pad_packed_sequencemediumCVSS 5.3EPSS 0.2%
- CVE-2025-2999: PyTorch memory corruption in unpack_sequence and pad_packed_sequencemediumCVSS 5.3EPSS 0.2%
- CVE-2025-2148: PyTorch memory corruption in profiler Tuple HandlermediumCVSS 5EPSS 0.4%
- CVE-2025-2149: PyTorch improper initialization in Quantized Sigmoid ModulemediumCVSS 4EPSS 0.3%
- CVE-2025-2953: PyTorch denial of service in torch.mkldnn_max_pool2dlowCVSS 3.3EPSS 0.3%
Vulnerabilities per week
The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 29 Jun 2026 | 0 | 0 | |
| 6 Jul 2026 | 0 | 0 | |
| 13 Jul 2026 | 0 | 0 | |
| 20 Jul 2026 | 1 | 0 | |
| 27 Jul 2026 | 0 | 0 | |
| 3 Aug 2026 | 0 | 0 | |
| 10 Aug 2026 | 0 | 0 | |
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 |
How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/vendors/pytorch.json, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "PyTorch vulnerabilities", https://junglewise.ai/threats/vendors/pytorch, 26 September 2026.