Cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) provides a convenient and scalable alternative to traditional cuff-based measurements. While prior studies have predominantly emphasized point-wise accuracy, calibration stability and long-term trend estimation-crucial for practical wearable applications-remain less explored. In this paper, we present a cuffless BP estimation approach combining a 1D EfficientNet regressor with a ridge regression calibration layer (RidgeCalib). We evaluated this system on a dataset of 243 participants undergoing synchronized PPG and reference BP monitoring over 24 hours. Our results indicate that the proposed framework effectively tracks general BP trends and that RidgeCalib significantly reduces prediction errors compared to the uncalibrated baseline. Despite these improvements, calibration drift still occurred over time, highlighting the limitations of single-point calibration methods. Overall, our findings underscore the potential of single-site PPG for continuous BP monitoring, while emphasizing the need for adaptive calibration strategies to further enhance reliability.

Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning.Both of them harness taskirrelevant features of data in their implementation.Text style is a feature that is naturally irrelevant to most NLP tasks, and thus suitable for adversarial and backdoor attacks.In this paper, we make the first attempt to conduct adversarial and backdoor attacks based on text style transfer, which is aimed at altering the style of a sentence while preserving its meaning.We design an adversarial attack method and a backdoor attack method, and conduct extensive experiments to evaluate them.Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer-the attack success rates can exceed 90% without much effort.It reflects the limited ability of NLP models to handle the feature of text style that has not been widely realized.In addition, the style transfer-based adversarial and backdoor attack methods show superiority to baselines in many aspects.All the code and data of this paper can be obtained at https:// github.com/thunlp/StyleAttack.

Tuhin Chakrabarty, Xurui Zhang, Smaranda Muresan, Nanyun Peng. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Word sense disambiguation (WSD) is a fundamental natural language processing task.Unsupervised knowledge-based WSD only relies on a lexical knowledge base as the sense inventory and has wider practical use than supervised WSD that requires a mass of sense-annotated data.HowNet is the most widely used lexical knowledge base in Chinese WSD.Because of its uniqueness, however, most of existing unsupervised WSD methods cannot work for HowNetbased WSD, and the tailor-made methods have not obtained satisfying results.In this paper, we propose a new unsupervised method for HowNet-based Chinese WSD, which exploits the masked language model task of pre-trained language models.In experiments, considering existing evaluation dataset is small and out-of-date, we build a new and larger HowNet-based WSD dataset.Experimental results demonstrate that our model achieves significantly better performance than all the baseline methods.All the code and data of this paper are available at https://github.com/thunlp/SememeWSD.