AI · Article
IBM Releases Two Experimental AI Models That Separate Instructions From Source Text to Resist Hidden Attacks
코인리더스 ·

At a glance
IBM has released two experimental AI models that read instructions and reference material separately. The goal is to keep hidden malicious commands in documents or tool outputs from changing what the AI is supposed to do. The models were published on the Hugging Face technical blog.
Key points
- The two models are 3B and 8B versions based on Granite 4.1.
- They were trained to read and generate LLMON, a format that splits input into instruction, reference, and output-condition blocks.
- IBM says they resist malicious instructions better in several tests, but defenses against attacks that change over multiple conversations are still being improved.
- The 3B model supports 12 languages, including Korean, and is released under the Apache 2.0 license.
Why it matters
Keeping AI from being steered by hidden commands in documents and external tools can make business AI assistants and agents safer to use.
Original source
IBM, 지시와 자료 나눠 읽는 AI 모델 2종…숨은 악성 지시 대응 실험
코인리더스 · Nov 14, 09:20 KST
Read on 코인리더스 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 코인리더스.
More from this field
- Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Walter Writes AI Tool Rewrites AI Text to Sound More Human, Ad Test Shows
This short video is a sponsored ad for Walter Writes AI, a tool that rewrites AI-generated text so it reads more like a person wrote it. The creator says they ran a paragraph through its detector, rewrote the flagged parts, and compared the scores before and after.
TheAIGRID · Nov 21, 06:15 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST