With the development of Pre-trained Language Models (PLMs), a wide variety of Chinese NLP tasks benefit from the BERT structure. Unfortunately, Chinese BERT-based PLMs are vulnerable to adversarial attacks and expose robustness issues. It inspired numerous defense works devoted to improving the model robustness. However, existing pre-training methods incur substantial time costs, while fine-tuning methods need more evidence to demonstrate how well the target model has been defended. This work aims to bridge this gap. We propose RoFuBERT, a robust fine-tuning framework using fuzz testing for Chinese BERT-based PLMs. We extract Chinese pinyin, glyph, and synonym features of downstream NLP tasks during fine-tuning. We integrate them into fuzz testing and evaluate the testing completeness of the model under adversarial attacks. Finally, we retrain the model for robust fine-tuning. Our evaluation shows that RoFuBERT improves adversarial robustness efficiently. Compared with the two baselines, RoFuBERT takes only 0.13 times more time. The reduction of adversarial attack success rate is improved by 41.26 %, and the modification rate of the adversarial samples is improved by 16.19 %, on average.

A new type of asymptotic stability for nonlinear hybrid neutral stochastic systems with constant delays was investigated recently, where the criteria depended on the delays’ sizes. Unfortunately, developed theory so far is not sufficient to deal with challenging problems of the decay rate, time-varying delays, and nonautonomous issues. These problems have not been tackled in the existing literature. Consequently, under the weak constraints, this article focuses on the general decay, including the exponential stability and the polynomial stability, for nonlinear nonautonomous hybrid neutral stochastic systems with time-varying delays by the approach of the multiple degenerate functionals. Moreover, this article derives the interesting assertions related to the general$H_{\infty }$stability and the polynomial growth at most.

Carbon cycle of terrestrial ecosystem is one of the hot issues in global change science. And there are more difficult during study with agroecosystem because of the strong affect caused by human activities such as sowing, fertilizing and irrigation. In this study, a measurement is carried out in Guantao, Hebei Province, China, which is a typical argoecosystem station. In this paper, carbon dioxide fluxes in Guantao, were simulated by BIOME-BGC model as well, and the result was compared with the eddy covariance (EC) data. The result shows that the trend curves of simulated data and observation data were well matched in growing season of winter wheat in 2009.