Research on the security protection mechanism of transformer-based power data mining facing sequence sensitivity

View at publisher Summarise with VIRAT
Authors: Yixi Chen, Ye Liu, Taipeng Zhu, Fangfang Zhou
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study aims to address the issue of the Transformer model being vulnerable to adversarial attacks due to its sequence sensitivity in power load forecasting. By defining attention entropy, Top-k weights, and quantification metrics, the study analyzes the model's excessive reliance on key time points. A weighted projection gradient descent attack algorithm is proposed to specifically expose the model's vulnerabilities. Additionally, a defense mechanism based on adversarial training is constructed, integrating regularization through attention distribution diversity. Experimental results show that the defense model achieves a prediction accuracy of RMSE 45.3 MW and MAPE 3.2%, outperforming the standard model. Under a strong attack with ε=0.05, the performance drop is controlled within 20%, while attention entropy increases from 2.31 to 3.15, and the Top-5 weight decreases from 0.72 to 0.58. This confirms that the defense mechanism significantly enhances robustness by dispersing the attention distribution. The conclusion indicates that this method fundamentally improves model security while maintaining accuracy, providing an effective security protection solution for power data mining systems.

Fields of Study & Subjects

Adversarial Robustness in Machine Learning Smart Grid Security and Resilience Security and Verification in Computing

Publication details

Journal / source
International Conference on Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI)
Pages
144–144
Publication date
19 March 2026
Language
EN