CybersecurityAI Research2 min reading time

Once popular for attacking AI, ASCII smuggling is embraced by spammers

Ars Technica
Read full post
ASCII smuggling, a technique originally used to stealthily embed malicious prompts in AI attacks, has been adopted by spammers to bypass email spam filters by hiding keywords in invisible Unicode tags. Microsoft observed a surge in such spam detections starting February 2026, peaking at 2.5 million daily detections before declining in mid-May.

More on this story


More in Cybersecurity

Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach

Covered by 3 sources
Cybersecurity6 min read

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Covered by 2 sources
Cybersecurity5 min read

Every AI Incident Has Two Timelines. We Default To One

Forbes