# CVE-2026-10800: PaddlePaddle FastDeploy Weak Hash in MultimodalHasher

Source: https://junglewise.ai/threats/cve-2026-10800-paddlepaddle-fastdeploy-weak-hash-in-multimodalhasher  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-04. Updated: 2026-06-04  
License: CC BY 4.0 with a link back

CVE-2026-10800 · Severity: low · CVSS 3.6 · Published 2026-06-04

PaddlePaddle FastDeploy is a toolkit used for deploying machine learning models. A flaw in its caching mechanism allows different data inputs to be treated as identical if they share the same raw byte patterns, even if their structure or data types differ. This could lead to the system returning incorrect cached results, potentially causing the application to behave unpredictably or process data incorrectly.

Vendors: [PaddlePaddle](https://junglewise.ai/threats/vendors/paddlepaddle).

## Quick answers

**Is CVE-2026-10800 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-10800 being exploited in the wild.

**How severe is CVE-2026-10800?** Low severity, with a CVSS score of 3.6, published 4 June 2026.

**Which products and versions are affected?** PaddlePaddle FastDeploy up to 2.4.1.

**Is there a fix for CVE-2026-10800?** A patch was published on 2026-04-08: Fix merged into develop branch Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-10800 attacked?** It is attacked with local access, in a software library.

**Am I affected by CVE-2026-10800?** Check whether you run PaddlePaddle FastDeploy at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

A vulnerability exists in the `hash_features` function within `fastdeploy/multimodal/hasher.py` of PaddlePaddle FastDeploy up to version 2.4.1. The component uses `numpy.ndarray.tobytes()` to generate SHA-256 digests for cache keys in the Processor, Encoder, and Prefix cache managers. Because `tobytes()` only serializes raw element bytes and excludes metadata like 'shape' or 'dtype', different arrays (e.g., different dimensions or data types) that share the same underlying byte sequence result in identical hashes. An attacker with local access could potentially manipulate input data to trigger these collisions, leading to silent cache corruption and the retrieval of incorrect multimodal features. This has been addressed in commit 3749457 by prepending shape and dtype metadata to the hash payload.

## Affected products

- PaddlePaddle FastDeploy up to 2.4.1

## Timeline

- 2026-04-03: disclosed: Issue first reported on GitHub
- 2026-04-08: patched: Fix merged into develop branch
- 2026-06-04: advisory: CVE published

## References

- [https://github.com/PaddlePaddle/FastDeploy/](https://github.com/PaddlePaddle/FastDeploy/)
- [https://github.com/PaddlePaddle/FastDeploy/commit/374945747652a8d32965591c0c01a00c88b7067f](https://github.com/PaddlePaddle/FastDeploy/commit/374945747652a8d32965591c0c01a00c88b7067f)
- [https://github.com/PaddlePaddle/FastDeploy/issues/7196](https://github.com/PaddlePaddle/FastDeploy/issues/7196)
- [https://github.com/PaddlePaddle/FastDeploy/pull/7185](https://github.com/PaddlePaddle/FastDeploy/pull/7185)
- [https://vuldb.com/cve/CVE-2026-10800](https://vuldb.com/cve/CVE-2026-10800)
- [https://vuldb.com/submit/831452](https://vuldb.com/submit/831452)
- [https://vuldb.com/vuln/368249](https://vuldb.com/vuln/368249)