This article analyzes the impact of artificial intelligence (AI) and machine learning technologies on the development and transformation of cyberthreats and the creation of highly effective cyberdefense systems. Key trends in AI evolution are discussed, including data-, model-, application-, and human-centric approaches, and their role in shaping both defensive and offensive capabilities. It is shown that attackers actively use AI to automate reconnaissance, personalize attacks, evade detection systems, and conduct complex multi-stage cyberattacks. The main types of impact on machine learning systems are analyzed: data manipulation, adversarial examples, attacks on models and their infrastructure. Modern defense methods that improve model robustness, data security, and the resilience of AI systems are presented. The idea of ​​​​the need to integrate intelligent approaches at all levels of the cyberdefense architecture and develop trusted, interpretable, and resilient machine learning models to counter new classes of threats is put forward.

Keywords: artificial intelligence, cybersecurity, cyberattack, machine learning, innovation, security, information, protection

The article discusses the main approaches to solving computer vision problems using neural networks, focusing on their application to a wide range of tasks. It describes the types of problems addressed by computer vision, such as image classification, object detection, segmentation, and activity recognition. The functioning mechanisms of convolutional neural networks (CNNs) are explained in detail, highlighting key features like convolutional layers, pooling operations, and activation functions. The problem of selecting object detection models, which generalize the more studied problem of object classification, is examined in depth, along with an evaluation of the efficiency of various algorithms using metrics like mAP (mean Average Precision) and IoU (Intersection over Union). Modern approaches to training neural networks are discussed, including the use of pre-trained models, transfer learning methods, and fine-tuning techniques for domain-specific applications. The article describes the advantages and limitations of prominent CNN architectures such as ResNet, VGG, and EfficientNet, offering insights into their suitability for different tasks. Data augmentation methods, aimed at improving the generalization ability of models, are also considered, emphasizing their importance for addressing data scarcity challenges. Practical examples of computer vision applications in areas like facial recognition, autonomous driving, and medical diagnostics are provided to illustrate the real-world relevance of these methods. Additionally, the integration of computer vision algorithms into complex systems and workflows is analyzed, highlighting its transformative potential across industries. Finally, the article discusses the future directions for research in this domain, including advancements in unsupervised learning, real-time processing, and explainable AI in computer vision.

Keywords: computer vision, architecture, convolutional neural networks, digital image, object classification