咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >A Dual Relaxation Method for N... 收藏

A Dual Relaxation Method for Neural Network Verification

作     者:Xiong, Huanzhang Hou, Gang Qin, Yueyuan Wang, Jie Kong, Weiqiang 

作者机构:Dalian Univ Technol Sch Software Technol Dalian 116621 Peoples R China Key Lab Ubiquitous Network & Serv Software Liaonin Dalian 116621 Peoples R China 

出 版 物:《INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING》 (Int. J. Software Engineer. Knowledge Engineer.)

年 卷 期:2024年第34卷第8期

页      面:1199-1220页

核心收录:

学科分类:0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术(可授工学、理学学位)] 

主  题:Neural networks robustness verification formal methods dual-neuron relaxation 

摘      要:In the robustness verification of neural networks, formal methods have been used to give deterministic guarantees for neural networks. However, recent studies have found that the verification method of single-neuron relaxation in this field has an inherent convex barrier that affects its verification capability. To address this problem, we propose a new verification method by combining dual-neuron relaxation and linear programming. This method captures the dependencies between different neurons in the same hidden layer by adding a two-neuron joint constraint to the linear programming model, thus overcoming the convex barrier problem caused by relaxation for only a single neuron. Our method avoids the combination of exponential inequality constraints and can be computed in polynomial time. Experimental results show that we can obtain tighter bounds and achieve more accurate verification than single-neuron relaxation methods.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分