计算机应用与软件2026，Vol.43Issue(6)：119-125,7.DOI:10.3969/j.issn.1000-386x.2026.06.017
基于决策边界采样的神经网络对抗训练
ADVERSARIAL TRAINING OF NEURAL NETWORKS WITH DECISION BOUNDARY SAMPLING
摘要
Abstract
The decision surface of neural networks is high-dimensional,and the existing analytical methods are difficult to study its shape characteristics and inefficient.Traditional adversarial training is easily affected by uneven samples,which is difficult to reduce the vulnerability.In order to explore the source of vulnerability efficiently,this paper proposes a sampling method based on decision boundary.It avoided using high-dimensional function to analyze decision boundary by Monte Carlo method.In order to reduce the vulnerability,this paper proposed a new adversarial training method,which generated adversarial samples close to the decision boundary through different strategies to achieve data augmentation.The experimental results show that singularity is one of the potential sources of vulnerability and the improved method can effectively improve the robustness.关键词
决策边界/对抗样本/神经网络/蒙特卡洛/对抗训练Key words
Decision boundary/Adversarial examples/Neural network/Monte Carlo/Adversarial training分类
信息技术与安全科学引用本文复制引用
贾婧玥,金澎,王兵,陈兴元..基于决策边界采样的神经网络对抗训练[J].计算机应用与软件,2026,43(6):119-125,7.基金项目
国家自然科学基金项目(61003206). （61003206）
