Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2604.14604/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTHijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection — HN submissionhttps://news.ycombinator.com/item?id=48247507urn:hackerpapers:submission:2604.14604:48247507Sat, 23 May 2026 13:28:25 GMT<p>AI assistants can be hijacked and manipulated by inaudible sounds</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2604.14604/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CR