According to the company 50 up to 70 percent of incoming messages in gmail is spam, but learning engineering techniques help Google beat spam and phishing messages with accuracy that reaches 99,9%.
The latest engineering learning model improves the process by delaying selected messages (less than the average of 0,05% of messages) for further fishing analysis.
Google reports that the news models detection will also help to create new warnings delaying time accesss in the URL, showing users a warning question when they have click σε έναν ύποπτο σύνδεσμο. Καθώς εντοπίζονται νέα πρότυπα, τα νέα μοντέλα protectionThey will adapt and improve over time.
In addition, Google added external company alert warnings to prevent users from sending accidentally protected data to someone outside of their company.
Gmail will not stop sending, but with warnings it will be trying to delay it a bit, according to Google, as mechanical intelligence will alert Gmail if the recipient is an existing contact or someone with whom the sender interacts regularly.
Google also added new built-in defenses against ransomware and polymorphic malware, blocking millions of plug-ins distributed as email attachments post officeU.
Threats are identified by combining signalthe (flags) from unwanted messages (spam), malicious preletterand ransomware with attachment heuristics (emails that may be threats based on flags) and senders' digital signatures (already marked as malware).