Researchers expose multi-trigger trojan attack on robot task-planning LLMs

A team from Binghamton University demonstrated MuTRAP, a multi-trigger trojan that injects a backdoor into LLMs used for robot task planning, and presented the findings in two papers at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems.

Why it matters

Prioritize safety testing for LLM-controlled robots to detect trojan-enabled harmful actions.

For product managers

For your product

What does this mean for your product?

Try it on your product

Read at The Register

More from this issueAll AI news from 23 Oct →

OpenAI seeks $30B raise at $1.25T valuation, sources sayUnconfirmed

OpenAI Makes Decisions API Widely Available, Challenging TypeSafe’s JevAvailable now

Google launches Agent Compute Engine giving each Gemini agent its own microVMAnnounced

Anthropic releases Claude Duet proactive agent in research previewAnnounced

Get this every morning, written for your product.

Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.

Request an invite See how it works