The Geometry of Last-Layer Model Stealing
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:The Geometry of Last-Layer Model Stealing
Abstract:This paper uses geometry to explain how a machine learning model can be stolen using an already existing well-known method. The author has shown the exact conditions required to perfectly copy the final layer of a transformer network. When looking deeper into the hidden layers the author has explained clear limits. The author has also demonstrated that a hidden network cannot be fully reverse engineered just by looking at the final results. The research clearly maps out what can and cannot be stolen from a model.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.06854 [cs.LG] |
| (or arXiv:2606.06854v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.06854
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Snigdha Chandan Khilar [view email][v1] Fri, 5 Jun 2026 02:57:48 UTC (30 KB)
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios
Jun 8
-
FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models
Jun 8
-
Multi-Scale Feature Attention Network for Polymer Classification using THz Dual-Comb Spectroscopy
Jun 8
-
MacArena: Benchmarking Computer Use Agents on an Online macOS Environment
Jun 8
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.