Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Modelstamp, a lightweight Python library designed to verify the integrity of machine-learning artifacts and their runtime environments before deserialization. By associating serialized models with a JSON manifest containing a SHA-256 digest and runtime metadata, Modelstamp effectively addresses the verification challenges posed by evolving software environments. Evaluation across various drift scenarios demonstrated that Modelstamp reliably detects changes in dependencies while maintaining efficient verification times, establishing it as a crucial tool for ensuring artifact integrity in dynamic contexts.
Modelstamp reveals that verifying machine-learning artifacts against evolving environments can be done efficiently without sacrificing integrity, even as dependencies change.
Persisted machine-learning models can remain byte-identical while the software environments in which they are loaded evolve, creating a verification problem that artifact integrity checks alone cannot expose. This paper presents Modelstamp, a lightweight Python persistence library for verifying artifact integrity and represented runtime-environment state before deserialization. At persistence time, Modelstamp associates a serialized artifact with a sidecar JSON manifest containing a SHA-256 digest, runtime metadata, and installed versions from a bounded tracked-package set; a separately recorded model-relevant subset determines which package versions participate in drift comparison. Optional HMAC authentication supports workflows in which the producer and verifier share a secret key. At verification time, the artifact and represented current environment are checked against this recorded evidence before the model is deserialized. Modelstamp is evaluated using 14 controlled environment-drift scenarios, eight controlled trust-boundary scenarios, and an artifact-size scaling benchmark from 10 MiB to 1 GiB. The controlled drift experiments behaved as specified across relevant dependency changes, unchanged environments, and unrelated environmental changes, including broader noise controls. The trust-boundary experiments similarly confirmed both intended detections and expected limitations, including shared-key forgery and replay. Median verification time increased from 0.032 s at 10 MiB to 3.334 s at 1 GiB, with measured throughput of approximately 307-312 MiB/s in the benchmark environment. These results characterize Modelstamp as a complementary pre-deserialization reference-state verification control rather than as a replacement for dependency-management systems, malicious-model detection, safe deserialization, or public publisher authentication.