# LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters

arXiv: https://arxiv.org/abs/2605.13163 · HTML: https://mlsanity.com/paper/2605.13163/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [A First Look at Deep Learning Apps on Smartphones](https://mlsanity.com/paper/1812.05448/) (2018)
- [DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories](https://mlsanity.com/paper/2111.04625/) (2021)
- [Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Protection in Mobile Apps](https://mlsanity.com/paper/2002.07687/) (2020)
- [ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks](https://mlsanity.com/paper/2011.05905/) (2020)
- [NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation](https://mlsanity.com/paper/2305.00097/) (2023)
- [Recovering the Pre-Fine-Tuning Weights of Generative Models](https://mlsanity.com/paper/2402.10208/) (2024)
- [SLIP: Securing LLMs IP Using Weights Decomposition](https://mlsanity.com/paper/2407.10886/) (2024)
- [Smart App Attack: Hacking Deep Learning Models in Android Apps](https://mlsanity.com/paper/2204.11075/) (2022)

## Abstract (arXiv)

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.