Kill Chain Catalyst for Autonomous Red Team Operations in Dynamic Attack Scenarios DOI
Antonio Horta, A. Santos,

Ronaldo Goldshmidt

и другие.

Опубликована: Сен. 16, 2024

From the perspective of real-world cyber attacks, executing actions with minimal failures and steps is crucial to reducing likelihood exposure. Although research on autonomous attacks predominantly employs Reinforcement Learning (RL), this approach has gaps in scenarios such as limited training data low resilience dynamic environments. Therefore, Kill Chain Catalyst (KCC) been introduced: an RL algorithm that decision tree logic, inspired by genetic alignment, prioritizing experiences. Experiments reveal significant improvements failures, well increased rewards when using KCC compared other algorithms.

Язык: Английский

Multiple Alignments of Protein Families with Weak Sequence Similarity Within the Family DOI Open Access
Dimitrii O. Kostenko, Maria A. Korotkova, Eugene V. Korotkov

и другие.

Symmetry, Год журнала: 2025, Номер 17(3), С. 408 - 408

Опубликована: Март 9, 2025

Statistically significant multiple sequence alignment construction is an important task that has many biological applications. We applied the method for alignments of highly divergent sequences (MAHDS) to construct (MSAs) 490 protein families with less than 20% identity between family members. The uses random symmetric position–weight matrices (PWMs) and a genetic algorithm alignment. PWM symmetry essential because it makes PWMs comparable recoverable at all steps MAHDS algorithm, which reduces optimal MSA search optimization task. A Monte Carlo assess statistical significance resulting alignments. constructed MSAs was compared obtained using T-Coffee MUSCLE algorithms. results showed 476 families, created much more statistically MUSCLE, whereas 138 only could MSAs. These findings indicate calculate in cases when other methods create purely are, therefore, most appropriate proteins weak similarities amino acid annotation.

Язык: Английский

Процитировано

0

Revolutionizing Molecular Design for Innovative Therapeutic Applications through Artificial Intelligence DOI Creative Commons

Ahrum Son,

Jongham Park, Woojin Kim

и другие.

Molecules, Год журнала: 2024, Номер 29(19), С. 4626 - 4626

Опубликована: Сен. 29, 2024

The field of computational protein engineering has been transformed by recent advancements in machine learning, artificial intelligence, and molecular modeling, enabling the design proteins with unprecedented precision functionality. Computational methods now play a crucial role enhancing stability, activity, specificity for diverse applications biotechnology medicine. Techniques such as deep reinforcement transfer learning have dramatically improved structure prediction, optimization binding affinities, enzyme design. These innovations streamlined process allowing rapid generation targeted libraries, reducing experimental sampling, rational tailored properties. Furthermore, integration approaches high-throughput techniques facilitated development multifunctional novel therapeutics. However, challenges remain bridging gap between predictions validation addressing ethical concerns related to AI-driven This review provides comprehensive overview current state future directions engineering, emphasizing their transformative potential creating next-generation biologics advancing synthetic biology.

Язык: Английский

Процитировано

4

An Algorithm for Local Alignment of DNA and Protein Sequences DOI

Hristina Georgieva,

Stella Vetova,

Vеskа Gаnchеvа

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 73 - 86

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0

Kill Chain Catalyst for Autonomous Red Team Operations in Dynamic Attack Scenarios DOI
Antonio Horta, A. Santos,

Ronaldo Goldshmidt

и другие.

Опубликована: Сен. 16, 2024

From the perspective of real-world cyber attacks, executing actions with minimal failures and steps is crucial to reducing likelihood exposure. Although research on autonomous attacks predominantly employs Reinforcement Learning (RL), this approach has gaps in scenarios such as limited training data low resilience dynamic environments. Therefore, Kill Chain Catalyst (KCC) been introduced: an RL algorithm that decision tree logic, inspired by genetic alignment, prioritizing experiences. Experiments reveal significant improvements failures, well increased rewards when using KCC compared other algorithms.

Язык: Английский

Процитировано

0