Using traditional methods based on detection rules written by human security experts, there is a significant challenge in accurately detecting many network threats that are increasingly becoming sophisticated. In order to deal with the limitation of the traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads containing binary data as well as text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets, such as IP addresses and ports. Given the combination of these features, we ensemble a text 1D-CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique with the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC) currently operating in South Korea. The proposed model showed remarkable progress compared to previous studies, demonstrating a highly accurate classification performance with an F1-Score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute to help security agents in the field divert their time to analyzing more complex attack patterns.

Antibody-Drug Conjugates (ADCs) are a powerful therapeutic modality for cancer treatment. ADCs are multi-functional biologics in which a disease-targeting antibody is conjugated to an effector payload molecule through a linker. The success of currently used ADCs has been largely attributed to the development of linker systems which allow targeted release of cytocidal payload drugs inside cancer cells. Many lysosomal proteases are over-expressed in human cancers. They can effectively cleave a variety of peptide sequences, which can be exploited in the design of ADC linker systems. As a well-established linker, valine-citrulline-p-aminobenzyl carbamate (ValCitPABC) is used in many ADCs that are already approved or under preclinical and clinical development. Although ValCitPABC and related linkers are readily cleaved by cathepsins in the lysosome while remaining reasonably stable in human plasma, many studies have shown that they are susceptible to carboxylesterase 1C (Ces1C) in mouse and rat plasma, which hinders preclinical evaluation of the ADCs. Furthermore, neutropenia and thrombocytopenia, two of the most commonly observed dose-limiting adverse effects of ADCs, are believed to result from the premature hydrolysis of ValCitPABC by human neutrophil elastase. In addition to cathepsin-cleavable linkers, there is also growing interest in legumain-sensitive linkers for ADC development. Increasing plasma stability while maintaining lysosomal cleavability of ADC linkers is an objective of intensive current research. This review reports recent advances in the design and structure-activity relationship studies of various peptide/peptidomimetic linkers in this field.

This article introduces a novel payload structure, which has been experimentally proven to have smaller impact force while the carried internal electronics remains intact. The study describes in details how materials and geometric structures were chosen based on information analysis. It is clarified how possible geometric structures and materials can be chosen to yield optimal efficiency. Finite element method simulations were carried out to investigate the mechanical properties of several geometric structures, which has led to the dodecahedron form. For the frame, Polylactic Acid were chosen as an optimal material. A low air pressure test for parts of the structure, and also the whole structure were carried out with successful results. Drop tests, with force measuring sensors and high speed videos, were carried out for measuring and comparing the maximal impact force of classical payloads and the novel one. Laboratory and real life tests demonstrated that the developed new structure is safer and it is applicable.