Phishing has been one of the most successful attacks in recent years. Criminals are motivated by increasing financial gain and constantly improving their email phishing methods. A key goal, therefore, is to develop effective detection methods to cope with huge volumes of email data. In this paper, a solution using BLSTM neural network and FastText word embeddings has been proposed. The solution uses preprocessing techniques like stop-word removal, tokenization, and padding. Two datasets were used in three experiments: balanced and imbalanced, whereas in the imbalanced dataset, the effect of maximum token size was investigated. Evaluation of the model indicated the best metrics: 99.12% accuracy, 98.43% precision, 99.49% recall, and 98.96% f1-score on the imbalanced dataset. It was compared to an existing solution that uses the DL model and word embeddings. Finally, the model and solution architecture were implemented as a browser plug-in.

Twenty six specimens of the polychaete Eulalia picta were found in finegrained sand tubes. Material was collected in the Antarctic fjord, Admiralty Bay at the depth of about 100 m. The comparison of tube sediment with the sediment composition at the collection site demonstrated that tubes were created with a high degree of particle selection. Our findings might suggest presence of the tube-building behavior in E. picta or show that this species is a highly specialized predator crawling into the tubes of other sessile polychaetes and uses their tubes as protective cases.