AIThe Registerabout 7 hours ago
Old-school text salting fools AI spam filters
3 min read
Attackers are using text salting to bypass LLM-powered email filters. Cybersecurity firm Barracuda detected over one million retail-themed phishing attacks using this technique since April. Text salting hides benign words to confuse AI systems, using CSS cropping, text manipulation, and zero font techniques to hide filler text from humans but not scanners.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
