Abstract:Foundation models and low-rank adapters enable efficient on-device generative AI but raise risks such as intellectual property leakage and model recovery attacks. Existing defenses are often impractical because they require retraining or access to the original dataset. We propose LoREnc, a training-free framework that secures both FMs and adapters via spectral truncation and compensation. LoREnc suppresses dominant low-rank components of FM weights, compensates for the missing information in authorized adapters, and further applies orthogonal reparameterization to obscure structural fingerprints of the protected adapter. Unauthorized users produce structurally collapsed outputs, while authorized users recover exact performance. Experiments demonstrate that LoREnc provides strong protection against model recovery with under 1% computational overhead.
| Comments: | Accepted to ICIP 2026 |
| Subjects: | Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.13163 [cs.CR] |
| (or arXiv:2605.13163v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13163 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Beomjin Ahn [view email]
[v1]
Wed, 13 May 2026 08:27:23 UTC (31,138 KB)