Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution

Computer Science > Cryptography and Security [Submitted on 17 Jun 2026] Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution Gabriele Digregorio, Marco Di Gennaro, Francesco Pastore, Stefano Zanero, Stefano Longari, Michele Carminati The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defenses. Current model-scanning solutions primarily rely on static, format-specific rules or known attack signatures, which limit their ability to generalize across frameworks and to detect novel exploitation paths. In contrast, we propose a solution that focuses on the effects an attack has on the host system executing the model and builds on foundational intuitions about ML model execution. In particular, we observe that ML models operate within well-defined lifecycle phases and that, within each phase, interactions with the host system are highly structured and predictable. We translate these intuitions into Moat, a dynamic lifecycle-aware approach for securing ML model execution, and instantiate this design in Re-Moat, our reference implementation. We evaluate Re-Moat across multiple ML frameworks using 77,974 real-world model artifacts from the Hugging Face Hub, 31 Proofs-of-Concept (PoCs) from CVEs, and 334 models from a state-of-the-art dataset, and compare it against state-of-the-art model-scanning solutions. Our results show that our approach detects all evaluated attack classes while maintaining a close-to-zero false-positive rate, validating our intuitions and motivating dynamic analysis for securing ML model execution. Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2606.19023 [cs.CR]   (or arXiv:2606.19023v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.19023 Focus to learn more Submission history From: Gabriele Digregorio [view email] [v1] Wed, 17 Jun 2026 12:49:22 UTC (52 KB) Access Paper: view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)