AI SecurityJul 16, 2026

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

Over 1M phishing emails evade AI security filters using hidden text salting techniques.

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.

AI summary of the linked source. Not reviewed by an editor. How this works

Read at source

The lesson from this incident

Full lesson

Threat actors are exploiting a fundamental weakness in how AI-powered email security tools parse and interpret obfuscated text, using a technique called 'text salting' to hide malicious phishing content from machine learning detectors. Over one million phishing emails have successfully evaded detection, demonstrating that over-reliance on AI-based filtering as a single layer of defense creates a dangerous blind spot. This attack is particularly insidious because the obfuscation is invisible or seamless to human recipients, meaning users remain the last line of defense. The incident underscores that AI security tools, while powerful, can be systematically manipulated and must not be treated as infallible gatekeepers. Organizations that have not trained employees to recognize phishing independently of their technical controls are especially vulnerable.

What helps against this

How we list vendors

AI application security
Prompt injection, data leaks through AI tools and unapproved AI use get caught.
For exampleCisco AI Defense Boomi AI Gateway Palo Alto Networks Prisma AIRS all options
Email security
Phishing, malware and invoice fraud are filtered out before they reach inboxes.
For exampleProofpoint Core Email Protection Check Point Harmony Email & Collaboration Cloudflare Email Security all options
Security awareness training and phishing simulation
People recognise and report attacks instead of falling for them.
For exampleHoxhunt Huntress Managed Security Awareness Training KnowBe4 Security Awareness Training all options

Indicators of Compromise

Extracted by AI from the linked source. Not reviewed by an editor. How this works

malware — text salting phishing

Entities

LLM-based email security filters (technology)text salting phishing campaign (campaign)