LoREnc：低秩加密用于保护基础模型和LoRA适配器
LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
AI总结：
LoREnc通过谱截断和补偿技术，在不重新训练的情况下保护基础模型和LoRA适配器，防止模型恢复攻击和知识产权泄露，实验表明其在1%计算开销下有效。
摘要：
基础模型和低秩适配器使设备端生成式AI高效，但存在知识产权泄露和模型恢复攻击的风险。现有防御方法往往不实际，因为需要重新训练或访问原始数据集。我们提出LoREnc，一种无需训练的框架，通过谱截断和补偿技术保护基础模型和适配器。LoREnc抑制基础模型权重中的主导低秩成分，补偿授权适配器中缺失的信息，并进一步应用正交重参数化以模糊受保护适配器的结构指纹。未经授权用户生成结构坍塌的输出，而授权用户可恢复精确性能。实验表明，LoREnc在1%的计算开销下提供强大的模型恢复防护。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
