THURSDAY, JULY 16, 2026 48° E  /  GLOBAL TECH · SUMMARISED SUBSCRIBE
AI, business, devices, policy — global tech, summarised every 30 minutes.
Security · 2h ago

Hidden Text in 1M+ Emails Bypasses AI Security Filters

By Meridian48 News Desk · Summarised from Dark Reading ·

Over 1 million phishing emails have used hidden text to evade AI-powered security filters. The technique, called text salting, inserts invisible characters that confuse large language models. Attackers exploit this to deliver malicious messages directly to inboxes.

Meridian48 take
The finding underscores how AI defenses remain vulnerable to simple adversarial tricks, highlighting the need for more robust detection methods.
Read the full reporting
1M+ Emails Use Hidden Text to Dupe AI Security Filters →
Dark Reading
phishingai-security
More security briefs
Go deeper on security
AllAIStartupsBusinessDevicesPolicySecurityDev ToolsPakistan