Text classification is widely studied in natural language processing (NLP). Deep learning models, including large pre-trained models like BERT and DistilBERT, have achieved impressive results in text classification tasks. However, these models’ robustness against adversarial attacks remains an area of concern. To address this concern, we propose three data augmentation methods to improve the robustness of such pre-trained models. We evaluated our methods on four text classification datasets by fine-tuning DistilBERT on the augmented datasets and exposing the resulting models to adversarial attacks to evaluate their robustness. In addition to enhancing the robustness, our proposed methods can improve the accuracy and F1-score on three datasets. We also conducted comparison experiments with two existing data augmentation methods. We found that one of our proposed methods demonstrates a similar improvement in terms of performance, but all demonstrate a superior robustness improvement.

Self-stabilization is a theoretical framework of non-masking fault-tolerant distributed algorithms. A self-stabilizing system tolerates any kind and any finite number of transient faults, such as message loss, memory corruption, and topology change. Because such transient faults occur so frequently in mobile ad hoc networks, distributed algorithms on them should tolerate such events. In this paper, we propose a self-stabilizing distributed approximation algorithm for the minimum connected dominating set, which can be used, for example, as a virtual backbone or routing in mobile ad hoc networks. The size of the solution by our algorithm is at most 7.6|D_opt|+1.4, where D_opt is the minimum connected dominating set. The time complexity is O(k) rounds, where k is the depth of input BFS tree.

This paper discusses the generalized local version of critical section problems including mutual exclusion, mutual inclusion, k-mutual exclusion and l-mutual inclusion. When a pair of numbers (l_i, k_i) is given for each process P_i, it is the problem of controlling the system in such a way that the number of processes that can execute their critical sections at a time is at least l_i and at most k_i among its neighboring processes and P_i itself. We propose the first solution for the generalized local (l_i, |N_i| + 1)-critical section problem (i.e., the generalized local l_i-mutual inclusion problem). Additionally, we show the relationship between the generalized local (l_i, k_i)-critical section problem and the generalized local (|N_i| + 1 − k_i, |N_i| + 1 − l_i)-critical section problem. Finally, we propose the first solution for the generalized local (l_i, k_i)-critical section problem for arbitrary (l_i, k_i), where 0 ≤ l_i < k_i + |N_i| + 1 for each process P_i.

The maximum leaf spanning tree (MLST) is a good candidate for constructing a virtual backbone in self-organized multihop wireless networks, but is practically intractable (NP-complete). Self-stabilization is a general technique that permits to recover from catastrophic transient failures in self-organized networks without human intervention. We propose a fully distributed self-stabilizing approximation algorithm for the MLST problem in arbitrary topology networks. Our algorithm is the first self-stabilizing protocol that is specifically designed to approximate an MLST. It builds a solution whose number of leaves is at least 1/3 of the maximum possible in arbitrary graphs. The time complexity of our algorithm is O(n ²) rounds.