CYBERSECURITYTRACKER
TRACKING6,506 stories in this site build1,309 vulnerability news stories in this site build
Permanent story citation

1M+ Emails Use Hidden Text to Dupe AI Security Filters

This page keeps the story as Cybersecurity Tracker first published it. If the tracker later corrects it, the correction appears below the original and never replaces it.

Back to newsStory 2728

As cited

Copy frozen at (site build).

ai security

1M+ Emails Use Hidden Text to Dupe AI Security Filters

Researchers have identified over one million emails using hidden text techniques called text salting to bypass AI-powered email security filters. The method exploits weaknesses in how large language models (LLMs) process obfuscated content, allowing phishing messages to reach user inboxes undetected.

Why it matters: Security teams relying on AI email filters need to understand this evasion technique impacts organizations across all industries; you should evaluate whether your email security provider has detection logic for text salting and consider supplementing with additional authentication controls.

Source published
First seen by Cybersecurity Tracker

Source attribution

Correction

Correction recorded as of .

ai security

1M+ Emails Use Hidden Text to Dupe AI Security Filters

Over one million emails are using hidden text techniques to evade artificial intelligence-based security filters. Text salting, a method that obscures content while remaining readable to humans, proves effective at bypassing AI-driven email defenses and allowing malicious messages to reach user inboxes.

Why it matters: Email administrators and security teams rely on AI filters to catch phishing, but this evasion technique puts all users at risk of delivery of deceptive messages that bypass those protections.

Source published
First seen by Cybersecurity Tracker

Source attribution

Glossary