通信学报2026，Vol.47Issue(4)：80-96,17.DOI:10.11959/j.issn.1000-436x.2026066
基于机器遗忘的模型能力细粒度访问控制机制
Fine-grained model capability access control mechanism based on machine unlearning
摘要
Abstract
A fine-grained model capability access control mechanism,named Model-Guard,was proposed to address the lack of capability access control in deployed artificial intelligence models,which may lead to unauthorized misuse of model capabilities.Without retraining,sensitive task-related parameters were identified by the selective synaptic dampen-ing(SSD)algorithm and attenuated to disable sensitive capabilities by default.An authorization factor calculation method was designed to restore model capabilities for authorized users.To ensure secure distribution of authorization fac-tors,a hybrid scheme combining symmetric encryption and ciphertext-policy attribute-based encryption(CP-ABE)was adopted,and a Bloom filter was introduced to reduce verification overhead.Experimental results demonstrated that Model-Guard achieved precise capability isolation and restoration in image recognition tasks.The proposed mechanism significantly reduces deployment and maintenance costs while enabling fine-grained and secure capability control.关键词
模型能力访问控制/选择性突触衰减算法/授权因子/属性基加密/布隆过滤器Key words
model capability access control/SSD/authorization factor/attribute-based encryption/Bloom filter分类
信息技术与安全科学引用本文复制引用
岳梓岩,许盛伟,王志强,杜皓华..基于机器遗忘的模型能力细粒度访问控制机制[J].通信学报,2026,47(4):80-96,17.基金项目
国家重点研发计划基金资助项目(No.2022YFB3104402) （No.2022YFB3104402）
中央高校基本科研业务费专项资金资助项目(No.3282025046) The National Key Research and Development Program of China(No.2022YFB3104402),The Fundamental Re-search Funds for the Central Universities(No.3282025046) （No.3282025046）
