You can now prevent malicious variants of
JavaScript exploits and phishing attacks embedded in webpages from
entering your network using machine learning (ML) on the firewall
dataplane.
URL filtering inline ML dynamically
analyzes and detects malicious contents by evaluating various webpage
details to formulate a high probability classification of a file.
This protection extends to currently unknown as well as future variants
of threats that match characteristics that Palo Alto Networks identified
as malicious.You configure the URL filtering inline ML models through
your URL Filtering profile but this requires a PAN-DB URL Filtering license.
Additionally, you can specify URL exceptions to exclude any false-positives
you encounter, which enables you to create more granular rules in
your profiles to support your specific security needs.