With the continuous influx of application software onto the application software market, achieving accurate software recommendations for users in the huge software application market is urgent. To address this issue, each application software market currently provides its own classification tags. However, several problems still exist, such as the lack of objectivity, hierarchy, and standardization in these classifications, which in turn affects the accuracy of precise software recommendations. Accordingly, a customized BERTopic model is proposed to cluster the software description texts of the application software and the automatic tagging and updating of the application software tags are realized according to the clusters obtained by topic clustering and the extracted subject words. At the same time, a data enhancement method based on the c-TF-IDF algorithm is proposed to solve the problem of imbalance of datasets, and then the classification model based on the BERT-BiLSTM model is trained on the labeled datasets to classify the software in the dimension of the application function, so as to realize the accurate software recommendation for users. Based on the experimental verification of two datasets, 21 categories in the SourceForge dataset and 19 categories in the Chinese App Store dataset are subclassed by the clustering results of the customized BERTopic model, and the tags of 138 subclasses and 262 subclasses are formed, respectively. In addition, a complete tagged software description text dataset is constructed and the software tags are updated automatically. In the first stage of the classification experiment, the weighted average accuracy, recall rate, and F1 value can reach 0.92, 0.91, and 0.92, respectively. In the second stage, the weighted average accuracy, recall rate, and F1 value can all reach 0.96. After data enhancement, the weighted average F1 value of the classification model can be increased by up to two percentage points.

Large language models (LLMs) have demonstrated significant capabilities in semantic understanding and code generation. However, cybersecurity tasks often require prompting the adaptation of open-source models to this domain. Despite their effectiveness, large-parameter LLMs incur substantial memory usage and runtime costs during task inference and downstream fine-tuning for cybersecurity applications. In this study, we fine-tuned six LLMs with parameters under 4 billion using LoRA (Low-Rank Adaptation) on specific cybersecurity instruction datasets, employing evaluation metrics similar to Hackmentor. Results indicate that post-fine-tuning, smaller models achieved victory or parity rates up to 85% against larger models like Qwen-1.5-14B on cybersecurity test datasets, with the best model reaching a 90% win or tie rate compared to SecGPT. Additionally, these smaller models required significantly less computational resources, reducing fine-tuning times by up to 53% and enhancing efficiency in downstream tasks. Further validation showed that with minimal fine-tuning, our models achieved a performance gain of 21.66% to 31.32% in tactical extraction and 30.69% to 40.42% in technical extraction tasks, significantly outperforming ChatGPT. These findings highlight the potential of smaller parameter LLMs for optimizing performance and resource utilization in cybersecurity applications including methods such as technique and tactic extraction. It will facilitate future research on the application of small-parameter large language models in the cybersecurity domain.