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

Summary

Researchers discovered that over 1 million phishing emails are successfully bypassing AI-powered email security filters by using text salting—a technique that hides malicious content from machine learning detectors while remaining visible or functional to recipients. The attack exploits weaknesses in how LLMs process obfuscated text, allowing threat actors to deliver phishing payloads undetected. This highlights a critical gap in current AI-based email security solutions.

Indicators of Compromise

• malware — text salting phishing

Entities