Tiếp theoHướng dẫn tiếp theo
Xâm nhập Prompt gián tiếp
kỹ thuật
HƯỚNG DẪN KỸ THUẬT
The sandwich defense repeats or restates the trusted task instruction after untrusted content has been inserted into a prompt.
Nghe hướng dẫn nàyAI thuật lại · ~3 min
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.
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.
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.
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.
Bản tin miễn phí
Ba câu chuyện AI đã được xác minh vào mỗi buổi sáng các ngày trong tuần, được viết bằng tiếng Anh đơn giản. Miễn phí mãi mãi, không có quảng cáo.
Một email mỗi ngày trong tuần. Hủy đăng ký trong một cú nhấp chuột. Chúng tôi không bao giờ bán hoặc chia sẻ địa chỉ của bạn.
Tự kiểm tra
Phản hồi tức thì về mọi câu trả lời và chứng chỉ có thể chia sẻ với ID có thể xác minh sau khi bạn vượt qua khóa học.
Hỗ trợ giáo dục AI miễn phí. AI Understanding là tổ chức phi lợi nhuận 501(c)(3) — không bao giờ có quảng cáo, không có tường phí. Hãy quyên góp
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.
The guide defines the pattern as a trusted task instruction before and after the untrusted passage.
The guide describes the reminder as a heuristic that may reinforce the task, not a guarantee.
The guide says sandwiching is a prompt-template change, not a model or permission change.
The guide explains that text repetition does not create a separate channel or structural access control.
The guide describes the preprint’s bounded setup: three model families, domains, and synthetic documents.
Tiếp tục học hỏi
Đã chọn thêm hướng dẫn cho chủ đề này
Tiếp theoHướng dẫn tiếp theo
Xâm nhập Prompt gián tiếp
kỹ thuật