公开(公告)号：US20220292200A1

公开(公告)日：2022-09-15

申请号：US17444612

申请日：2021-08-06

Applicant: Huazhong University of Science and Technology

Inventor： Deqing Zou ,  Jing Tang ,  Zhen Li ,  Hai Jin

IPC: G06F21/57 ,  G06F21/54 ,  G06F21/55 ,  G06K9/62 ,  G06N3/08

Abstract: The present invention relates a device for improving robustness of deep-learning based detection of source-code vulnerability, the device at least comprises a code-converting module, a mapping module, and a neural-network module, wherein the mapping module is in data connection with the code-converting module, the mapping module is in data connection with the neural-network module, respectively, and the neural-network module includes at least two first classifiers, based on a received first training program source code, the mapping module maps a plurality of code snippets, and the neural-network module trains the at least two first classifiers according to a first sample vector. The present invention improves the robustness of detection of source-code vulnerability by performing classification training on the feature generators and the classifiers.

公开(公告)号：US12026260B2

公开(公告)日：2024-07-02

申请号：US17444612

申请日：2021-08-06

Applicant: Huazhong University of Science and Technology

Inventor： Deqing Zou ,  Jing Tang ,  Zhen Li ,  Hai Jin

IPC: G06F21/00 ,  G06F18/214 ,  G06F21/54 ,  G06F21/55 ,  G06F21/56 ,  G06F21/57 ,  G06N3/08 ,  G06N3/094

CPC classification number: G06F21/577 ,  G06F18/214 ,  G06F21/54 ,  G06F21/554 ,  G06F21/563 ,  G06N3/08 ,  G06N3/094

Abstract: The present invention relates a device for improving robustness of deep-learning based detection of source-code vulnerability, the device at least comprises a code-converting module, a mapping module, and a neural-network module, wherein the mapping module is in data connection with the code-converting module, the mapping module is in data connection with the neural-network module, respectively, and the neural-network module includes at least two first classifiers, based on a received first training program source code, the mapping module maps a plurality of code snippets, and the neural-network module trains the at least two first classifiers according to a first sample vector. The present invention improves the robustness of detection of source-code vulnerability by performing classification training on the feature generators and the classifiers.