.png){kind=icon}
返回
Parameter Interpolation Adversarial Training for Robust Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TIFS.2025.3533925.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks. However, existing adversarial training methods show that the model robustness has apparent oscillations and overfitting issues in the training process, degrading the defense efficacy. To address these issues, we propose a novel framework called Parameter Interpolation Adversarial Training (PIAT). PIAT tunes the model parameters between each epoch by interpolating the parameters of the previous and current epochs. It makes the decision boundary of model change more moderate and alleviates the overfitting issue, helping the model converge better and achieving higher model robustness. In addition, we suggest using the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the relative magnitude of logits between clean and adversarial examples rather than the absolute magnitude. Extensive experiments conducted on several benchmark datasets demonstrate that our framework could prominently improve the robustness of both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs).
Keyword:
Training
Robustness
Overfitting
Computational modeling
Oscillators
Interpolation
Accuracy
Perturbation methods
Mean square error methods
Optimization
Adversarial examples
adversarial training
parameter interpolation
normalized mean square error
期刊
IF:
8
论文数:
5.2K
被引数:
2.3W
机构
引用论文
Effect of viscosity on the electrical properties of conducting thermoplastic composites made by compression molding of a powder mixture粘度对通过粉末混合物的压缩成型制成的导电热塑性复合材料的电性能的影响
.png){kind=icon}
PREAI
分享收藏
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏分享收藏Research on the Efficiency of Wireless Power Transfer System Based on Multi-Auxiliary Transmitting Coils基于多辅助发射线圈的无线电能传输系统效率研究
PREAI
分享收藏
查看更多内容