An attack in which hidden or malicious instructions in a document, web page or email trick an AI system into ignoring its rules or leaking data. Defences include limiting permissions, filtering inputs and requiring human approval for sensitive actions.
Chatbot yang seharusnya membantu karyawan bisa dalam hitungan menit menyarankan tindakan yang bias atau menyesatkan, dan satu kalimat tersembunyi dalam permintaan sudah cukup untuk membelokkan asisten AI. Episode ini menjelaskan cara kerja prompt injection…
Community wiki
Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.
Experts and companies for this topic
Nobody has listed this topic yet. Add it to your profile.
Kami memakai Microsoft Clarity untuk analisis penggunaan.