AIBearisharXiv – CS AI · Feb 277/107
🧠
Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation
Researchers discovered a vulnerability in AI music and video generation systems where phonetic prompts can bypass copyright filters. The 'Adversarial PhoneTic Prompting' attack achieves 91% similarity to copyrighted content by using sound-alike phrases that preserve acoustic patterns while evading text-based detection.
$NEAR$APT