Presentación del libro en españolinteligencia artificial

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR CYBERSECURITY

Name: ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR CYBERSECURITY
Author: Faramarz Kowsari

Foundations, Intelligent Threat Detection, Adversarial Machine Learning, Privacy, Generative AI, and Secure Autonomous Systems

“ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR CYBERSECURITY” es un libro de Faramarz Kowsari dentro del área de inteligencia artificial. Esta página de descubrimiento en español organiza la información pública del libro para que sus temas, público, idioma real de publicación y vías oficiales de lectura o compra sean más fáciles de encontrar.

Los metadatos públicos sitúan este título en temas de inteligencia artificial, herramientas modernas de IA o flujos de trabajo basados en prompts.

Idioma de publicación: inglés. Esta es una página de orientación en español. El libro se publica en inglés; el título, la vista previa y las opciones de compra de Google Books corresponden a esa edición.

Ver en Google Books Abrir vista previa gratuita Página original del libro

¿De qué trata este libro?

Los metadatos públicos sitúan este título en temas de inteligencia artificial, herramientas modernas de IA o flujos de trabajo basados en prompts.

Temas destacados

Artificial intelligence in cybersecurityMachine learning for threat detectionNetwork intrusion detectionMalware and ransomware analysisPhishing and DNS securityEndpoint, cloud and container telemetrySecurity data engineeringData leakage and time-based validationPrecision, recall, calibration and concept driftGraph neural networks and attack graphsAdversarial machine learning and data poisoningModel extraction and model supply-chain securityDifferential privacy and federated learningLarge language model (LLM) security

Descripción pública original del libro

inglés

Artificial Intelligence and Machine Learning for Cybersecurity is an English-language, 473-page graduate-level textbook organized into 70 chapters and ten connected parts. It begins with security objectives, threat modeling, networks, cryptography, logs and incident response, then builds the necessary Python, probability, statistics, machine learning and deep learning foundations. Security telemetry, temporal feature engineering, class imbalance, data leakage, calibration, uncertainty and reproducibility form the methodological bridge to applied threat detection. The applied chapters connect models to recognizable cybersecurity evidence: network flows, encrypted-traffic metadata, anomalies, malware files and behavior, ransomware, phishing, malicious URLs and DNS, identity misuse, botnets, DDoS, cloud and container events, digital forensics and threat intelligence. Further sections examine graph-based attack analysis, concept drift, operational technology, connected vehicles, defensible autonomous response and causal reasoning. Throughout, the distinction between a model prediction and an authorized operational decision remains central. The advanced sequence studies adversarial examples, problem-space evasion, poisoning, model extraction, robust evaluation and AI supply-chain integrity, followed by membership inference, differential privacy, federated learning and privacy-preserving techniques. The final chapters address generative AI, retrieval-augmented security intelligence, prompt injection, LLM application security, red teaming, agent permissions, MCP, SOC copilots, secure MLOps, model incidents, human factors, edge deployment, research design, an end-to-end capstone and post-quantum security. Python examples, explanatory figures and illustrative scenarios are…

¿A quién va dirigido?

El público objetivo se basa en la descripción pública del libro. Para lectores hispanohablantes, conviene tener presente que la edición disponible está publicada en inglés.

For master's-level AI and cybersecurity students, instructors, researchers, software engineers, security analysts and independent learners who want a structured bridge between machine learning theory, cybersecurity telemetry, defensible evaluation and secure AI system deployment.

Objetivos de aprendizaje publicados