PofoliaShared via Pofolia

Zenodo (CERN European Organization for Nuclear Research)· 2026

Maya-LLM-Defence: Sovereign Military LLM with Affective SNN Safety Substrate

Venkatesh Swaminathan

Short summary

Maya-LLM-Defence, a safety layer for offline military LLMs, blocks 28.33% of jailbreak prompts within 0-1ms using four spiking neurons, without impacting legitimate traffic.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Information Systems and ManagementDecision Sciences