Skip to content
HomeBriefFor youTrackersTopicsCompaniesGlossaryNewsletterSecurityHealth & medicineFinance & marketsRoboticsModels & researchPolicy & regulationEnterprise & businessDeveloper tools
Security · Nov 14, 2026 · 3 min read

IBM's Granite 4.1 LLMON previews train the model to separate instructions from data, claiming near-zero indirect prompt-injection success. What security teams should test

Reserved special tokens that user content cannot forge, and unique IDs that bind each instruction to the data it may act on: it is the first vendor attempt to make injection resistance a property of the model rather than of the prompt.

Why it matters
SecurityRun your own indirect-injection corpus against the 8B preview this week. If the attack success rate collapses on your documents the way IBM says it does on OPI, you have a candidate for the parsing layer in front of your agents.
ML engineersThe novelty is structural: delimiters are reserved tokens, so no text in a retrieved document can open or close a tag. The weakness IBM admits is that the behaviour is learned, so adaptive multi-turn attacks and post-fine-tuning drift are untested.
DevelopersJSON converts to LLMON and back losslessly. Wrapping a tool-calling pipeline is a formatting change; the GitHub toolkit has templates. Keep the output validator you already have.

Prompt injection has resisted every fix because the model cannot tell where the instruction ends and the data begins. A system prompt says 'treat the following as data'; a retrieved web page says 'ignore the above'; both are text, and the model weighs them the same way. On Wednesday IBM published two experimental models, granite-4.1-3b-llmon-preview and granite-4.1-8b-llmon-preview, trained on a format designed to remove that ambiguity, and reported results that would matter a great deal if they hold up.

What LLMON is

LLM Object Notation, pronounced 'lemon', is an XML-like markup for prompts. Two features do the work. First, the structural delimiters are reserved special tokens in the vocabulary, not ordinary characters, so nothing in user or retrieved content can produce an opening or closing tag; the classic injection trick of mimicking a system marker is impossible at the tokeniser level. Second, tags carry semantic roles, instructions, data, requirements, and unique IDs bind each instruction to the specific data it is allowed to act on, in the way a function's arguments are bound to its parameters. Content that is not referenced by the execution block is meant to be ignored. Existing JSON converts to LLMON and back without loss, and IBM says the format complements chat templates rather than replacing them.

The numbers

On OPI, a benchmark of indirect prompt injections hidden in retrieved content, IBM reports that attack success for the LLMON models drops to nearly zero, while the non-LLMON baselines it tested remain highly susceptible. Expressed as robustness, the LLMON models avoid 47% more attacks than the best frontier model IBM tested and 95% more than the best open-source model. Similar trends are reported on the ASB and StruQ benchmarks. On standard capability benchmarks the previews perform on par with the Granite 4.1 Instruct models, so the resistance does not appear to cost utility. The exact per-model figures are in charts rather than text, and IBM has not named the frontier model it compared against.

The caveats IBM states

This is an experimental preview for evaluation, not production. The injection resistance is 'a learned behavior, not an enforced guarantee': the model has been trained to ignore unreferenced instructions, but nothing in the architecture prevents it from obeying one. The benchmarks cover static indirect injections; adaptive attacks that unfold over multiple turns are still being studied. And the rule that unreferenced content is ignored is itself learned. Those are the honest limits of the approach, and they are the same limits that apply to every other training-based defence.

Why it still matters

The difference from previous defences is where the boundary lives. Guardrail classifiers sit outside the model and can be evaded; system-prompt instructions compete with injected text on equal footing. Reserved-token delimiters move part of the boundary into the tokeniser, where text cannot reach it, and the binding of instructions to data gives the model a reason to ignore an instruction rather than a request to. If the learned behaviour proves robust, a 3B model that can be run on-premises with a measurable injection rate is exactly what regulated deployments of RAG and agents have lacked.

What to test

Take your own indirect-injection set, the payloads that have actually worked against your retrieval pipeline, convert the prompts to LLMON with IBM's toolkit and measure attack success on both previews against your current model. Then try to break the binding: instructions that reference the wrong data ID, injected text that claims an ID, and multi-turn sequences that build up context before the payload. Fine-tune the 3B model on a small task and re-run the injection set to see whether the resistance survives. Report what you find in IBM's GitHub Discussions; the company has asked for it, and the field needs the adaptive-attack results more than another benchmark.

Key terms in this story

  • Indirect prompt injection An attack in which malicious instructions are hidden in content the model reads (a web page, email, document or tool result) rather than typed by the user.
  • Reserved special token A vocabulary entry a model's tokeniser treats as a control symbol rather than text, so no user or document content can produce it.
  • Prompt injection An attack in which text the model reads, such as a web page or email, contains instructions that hijack its behaviour.
  • Frontier model A model at or near the state of the art at the time, typically the newest top tier from a major lab.
  • System prompt Standing instructions a developer gives a model that apply to every conversation, such as persona, rules and output format.
All 99 terms →
securitymodelsresearchagents
Written in our own words from the linked sources · updated 2026-11-14 · corrections: corrections@aibriefing.io

Get the brief in your inbox

One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.

Published daily by AI Briefing. We never share your address.
Like this? Get tomorrow's brief by email, free.