PANDUAN Teknikal

Pertahanan Sandwich untuk Promp

The sandwich defense repeats or restates the trusted task instruction after untrusted content has been inserted into a prompt.

Dengar panduan iniAI-diceritakan · ~3 min

Pada halaman ini3 min dibaca
  1. Gambaran keseluruhan
  2. Menyelam dalam
  3. Pelaksanaan Dunia Sebenar
  4. The Future of The Sandwich Defense for Prompts
  5. Mempraktikkannya
  6. Teruskan Meneroka
  7. Soalan lazim

Gambaran keseluruhan

The closing reminder may reinforce the intended task, but it remains text-based guidance inside the same model context and cannot guarantee that an injection will be ignored.

Menyelam dalam

The sandwich defense places untrusted content between an initial trusted task instruction and a closing repetition or restatement of that instruction. For example, a prompt may ask for a summary, insert an external page, and then remind the model to summarize the page rather than follow directions inside it. This is a prompt-template change: it does not modify the model, create a separate data channel, or restrict tool access. It is easy to test, but it should be treated as a heuristic rather than a security boundary. The intuition is that the final reminder may help the model focus on the intended task after reading the untrusted passage. That does not mean models always follow the last instruction, nor that the closing reminder structurally outranks hostile text. A malicious passage may imitate trusted instructions, contain multiple directives, or exploit behavior not covered by the template. The defense can also fail if the untrusted block enters context through another route that the prompt author did not account for. Evidence is model- and attack-dependent. A 2026 preprint tested prompt sandwiching and other prompt-level defenses against domain-camouflaged injection across three model families and three synthetic deployment domains. It found substantial variation by model, and none of the tested prompt-level defenses eliminated the threat across weaker models. The study is limited to its setup; it is evidence against assuming a universal effect, not a complete ranking for every real system. Use sandwiching only as one layer alongside explicit data handling, permission checks on tools, attack testing, and user confirmation for consequential actions. Measure both resistance and task quality before release.

Pelaksanaan Dunia Sebenar

A translation prompt gives the task, inserts a user-provided paragraph, then repeats that the paragraph should be translated rather than obeyed.

A document question-answering workflow states the question, includes a retrieved passage, and restates the requested answer format before generation.

A summarizer tells the model to summarize a forum post, places the post in a marked region, then closes by reiterating that post text is source material.

A security test compares a sandwich prompt with a baseline using the same benign and malicious documents across several model versions.

The Future of The Sandwich Defense for Prompts

Prompt-level defenses will remain attractive because they are quick to prototype, but their value will depend on model behavior and the attacks a system encounters. As evaluations improve, teams may get better evidence about when repetition helps. The lasting lesson is to test this pattern within a layered design and retain deterministic limits on what an agent can do. New models may respond differently to the same closing reminder, so validate updates before relying on them. Keep safeguards outside the prompt for consequential actions.

Mempraktikkannya

Mengapa ia penting

  • Kos dan bajet. Keputusan seni bina memacu prestasi dan kos operasi selama bertahun-tahun.
  • Keputusan yang lebih jelas. Pendidikan teknikal membantu pasukan memilih timbunan yang betul, bukan hanya yang terbaharu.
  • Kawalan kualiti. Pilihan kejuruteraan yang lebih baik mengurangkan insiden kebolehpercayaan dalam pengeluaran.

Berhati-hati untuk

  • Mengoptimumkan satu penanda aras boleh menyembunyikan kelemahan sistem yang lebih luas.
  • Kos infrastruktur dan penyelenggaraan sering dipandang remeh.
  • Jurang keselamatan dan pemerhatian boleh berkembang apabila sistem menjadi lebih kompleks.

Langkah seterusnya

  1. Tentukan sasaran kependaman, kualiti dan kos sebelum pelaksanaan.
  2. Penanda aras di bawah beban realistik dan keadaan data.
  3. Pemantauan instrumen untuk ralat, drift dan kesan pengguna.
  4. Sediakan laluan balik dan tindak balas insiden sebelum penskalaan.

Teruskan Meneroka

Newsletter percuma

Dapatkan taklimat AI harian

Tiga cerita AI yang disahkan setiap pagi hari bekerja, ditulis dalam Bahasa Inggeris biasa. Percuma selamanya, tiada iklan.

Satu e-mel setiap hari bekerja. Berhenti melanggan dalam satu klik. Kami tidak pernah menjual atau berkongsi alamat anda.

Uji diri anda

Take the The Sandwich Defense for Prompts quiz

Maklum balas segera pada setiap jawapan, dan sijil yang boleh dikongsi dengan ID yang boleh disahkan sebaik sahaja anda lulus kursus.

Mulakan kuiz

Sokong pendidikan AI percuma. AI Understanding ialah pertubuhan bukan keuntungan 501(c)(3) — tiada iklan, tiada bayaran dinding, selamanya. Buat derma

Soalan lazim

What is The Sandwich Defense for Prompts?

The sandwich defense repeats or restates the trusted task instruction after untrusted content has been inserted into a prompt. The closing reminder may reinforce the intended task, but it remains text-based guidance inside the same model context and cannot guarantee that an injection will be ignored.

Di manakah pertahanan sandwic meletakkan arahan tugasan berulang?

Panduan mentakrifkan corak sebagai arahan tugasan yang dipercayai sebelum dan selepas laluan yang tidak dipercayai.

Bagaimanakah peringatan penutup boleh membantu dalam corak ini?

Panduan menerangkan peringatan sebagai heuristik yang mungkin menguatkan tugas, bukan jaminan.

Apakah perubahan sandwic dalam aplikasi?

Panduan mengatakan sandwic ialah perubahan templat segera, bukan perubahan model atau kebenaran.

Mengapa pertahanan sandwic bukan sempadan keselamatan?

Panduan ini menerangkan bahawa pengulangan teks tidak mewujudkan saluran berasingan atau kawalan capaian struktur.

Apakah yang dinilai oleh pracetak penyamaran domain yang disebut?

Panduan ini menerangkan persediaan sempadan pracetak: tiga keluarga model, domain dan dokumen sintetik.