Learn languages naturally with fresh, real content!

Popular Topics
Explore By Region
AI-powered browsers are vulnerable to hidden text attacks that trick AI into leaking data or visiting malicious sites, bypassing traditional security.
AI-powered web browsers face rising security risks from prompt injection attacks, where hidden text in web pages or images tricks AI into leaking data or visiting malicious sites without user knowledge.
Researchers and Brave Software demonstrated that faint text in images—like light blue on yellow—can command AI browsers such as Perplexity’s Comet and Fellou to perform harmful actions, even when users see nothing suspicious.
Unlike traditional malware, these attacks bypass antivirus software since no code runs on the device.
While Perplexity patched the flaw after a report, it criticized Brave’s public warning as alarmist.
Experts urge users to disable AI features and keep systems updated, as browser makers race to address systemic vulnerabilities in AI-driven browsing.
Los navegadores impulsados por IA son vulnerables a los ataques de texto oculto que engañan a la IA para que filtre datos o visite sitios maliciosos, eludiendo la seguridad tradicional.