微信服务号

微信订阅号

2025-5-15- 10
Home > Archive>Volume 36, Issue 8, 2025 >1-18. DOI:10.13328/j.cnki.jos.007344
PDF HTML XML Export Cite reminder
Incremental Verification for Neural Network
Author:
Affiliation:

Clc Number:

TP311

  • Article
    • | |
  • Metrics
    • |
  • Reference
    • |
  • Related [20]
    • |
  • Cited by
    • | |
  • Comments
    Abstract:

    Constraint solving is a fundamental approach for verifying deep neural network (DNN). In the field of AI safety, DNNs often undergo modifications in their structure and parameters for purposes such as repair or attack. In such scenarios, the problem of incremental DNN verification is proposed, which aims to determine whether a safety property still holds after the DNN has been modified. To address this, an incremental satisfiability modulo theory (SMT) algorithm based on the Reluplex framework is presented. The proposed algorithm, DeepInc, leverages the key features of the configurations from the previous solving procedure, heuristically checking whether these features can be applied to prove the correctness of the modified DNN. Experimental results demonstrate that DeepInc outperforms Marabou in terms of efficiency in most cases. Moreover, for cases where the safety property is violated both before and after modification, DeepInc achieves significantly faster performance, even when compared to the state-of-the-art verifier α, β-CROWN.

    Reference
    Cited by
Get Citation

刘宗鑫,迟智名,赵梦宇,黄承超,黄小炜,蔡少伟,张立军,杨鹏飞.神经网络的增量验证.软件学报,2025,36(8):1-18

Copy
Share
Article Metrics
  • Abstract:119
  • PDF: 194
  • HTML: 0
  • Cited by: 0
History
  • Received:August 23,2024
  • Revised:October 14,2024
  • Online: December 10,2024
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the firstVisitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063