Kuis Serangan Injeksi Cepat

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

1. Which trust failure can a prompt-injection attempt exploit?
   • Adversarial instructions in task material being followed as authoritative commands
   • A requirement that every model encrypt its entire context
   • A guarantee that all models have administrator privileges
   • A requirement that every model always obey every input
2. Apa perbedaan injeksi cepat INDIRECT dengan injeksi langsung?
   • Ini hanya berfungsi pada model gambar
   • Ini memerlukan akses fisik ke server
   • Instruksi berbahaya berada di sumber eksternal yang kemudian dibaca oleh model, bukan di pesan pengguna sendiri
   • Itu dilakukan oleh pengembang dengan sengaja
3. Which availability goal does the cited indirect-injection taxonomy include?
   • Only stealing an entire training corpus in every attack
   • Inhibiting useful responses or disrupting a search task
   • Only changing a GPU’s physical memory size
   • Only improving all authorized search results
4. How can least-privilege tool permissions limit a successful injection’s consequences?
   • They prove every allowed operation is harmless in every context
   • They guarantee the model never proposes an injected action
   • They remove the need for any output or action validation
   • They restrict the operations and resources available to the workflow
5. What behavior does the Instruction Hierarchy study aim to train?
   • Sorting all retrieved words alphabetically
   • Treating every webpage as more authoritative than the developer
   • Following privileged instructions over conflicting lower-priority content
   • Encrypting the model vocabulary with an image key
6. Mengapa injeksi cepat menjadi lebih berbahaya ketika agen AI memperoleh alat?
   • Agen yang tertipu kini dapat mengambil tindakan nyata seperti mengirim email, menjalankan kode, atau membocorkan data
   • Agen berjalan lebih lambat dengan alat
   • Alat membuat model melupakan pelatihannya
   • Alat menggandakan kebingungan model
7. Why should a prompt-injection evaluation cover images when an application accepts multimodal input?
   • Images guarantee that all instructions are trustworthy
   • An image can contain only one numerical scalar
   • Plain-text testing automatically covers every image input
   • Adversarial instructions can be embedded in an image channel
8. Why is merely quoting an attack instruction not enough to establish that an application was compromised?
   • Every quoted string necessarily changes system permissions
   • The text may be legitimate analysis material and may never be executed as an instruction
   • An attacker must modify all original model weights first
   • No authorized user can ever discuss a security attack