Read more
Real World AI in Cybersecurity provides hands on examples of using AI and machine learning to improve cybersecurity in systems of all sizes. It includes step-by-step guidance for using AI applications in system administration and cybersecurity. The more complex and frequent that cybersecurity attacks and data breaches become, the more cybersecurity experts will need to master tools including AI to help them spot the dangerous attacks and mitigate them.
The reader will learn to:
* Overcome antivirus limits in threat detection, classify suspicious user activity, and use fraud detection algorithms
* Use application performance monitoring (APM) tools and improve spam detection with advanced filtering techniques
* Pick the right Python libraries for AI
* Categorize advanced persistent threats (APT), zero-days, and malware samples
* Use python tools to turn logs into datasets for analysis, predict network intrusions, and spot fake logins and fake accounts
* Apply algorithms from AI for cybersecurity including decision trees, Bayesian classification, least squares regression and more
* Use Jupyter notebooks and the key tools including MLBase.jl, cikitLearn.jl, MachineLearning.jl and Mocha.jl
* Test data using AI to assess incident response
Summary
Real World AI in Cybersecurity provides hands on examples of using AI and machine learning to improve cybersecurity in systems of all sizes. It includes step-by-step guidance for using AI applications in system administration and cybersecurity. The more complex and frequent that cybersecurity attacks and data breaches become, the more cybersecurity experts will need to master tools including AI to help them spot the dangerous attacks and mitigate them.
The reader will learn to:
* Overcome antivirus limits in threat detection, classify suspicious user activity, and use fraud detection algorithms
* Use application performance monitoring (APM) tools and improve spam detection with advanced filtering techniques
* Pick the right Python libraries for AI
* Categorize advanced persistent threats (APT), zero-days, and malware samples
* Use python tools to turn logs into datasets for analysis, predict network intrusions, and spot fake logins and fake accounts
* Apply algorithms from AI for cybersecurity including decision trees, Bayesian classification, least squares regression and more
* Use Jupyter notebooks and the key tools including MLBase.jl, cikitLearn.jl, MachineLearning.jl and Mocha.jl
* Test data using AI to assess incident response
