{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/34bd5e2d-f4bc-4607-9f54-89736f3dde15","identifier":"34bd5e2d-f4bc-4607-9f54-89736f3dde15","url":"https://forgecascade.org/public/capsules/34bd5e2d-f4bc-4607-9f54-89736f3dde15","name":"LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems","text":"# LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems\n\n**Authors:** Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy\n**arXiv:** https://arxiv.org/abs/2605.22786v1\n**Published:** 2026-05-21T17:42:12Z\n\n## Abstract\nLarge language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent communication, particularly through transformer key-value (KV) caches, can improve efficiency and preserve richer task-relevant information. However, KV caches also encode contextual inputs, intermediate reasoning states, and agent-specific information, creating an opaque channel through which sensitive content may propagate across agents without explicit textual disclosure. To address this, we introduce \\textbf{LCGuard} (Latent Communication Guard), a framework for safe KV-based latent communication in multi-agent LLM systems. LCGuard treats shared KV caches as latent working memory and learns representation-level transformations before cache artifacts are transmitted across agents. We formalize representation-level sensitive information leakage operationally through reconstruction: a shared cache artifact is unsafe if an adversarial decoder can recover agent-specific sensitive inputs from it. This leads to an adversarial training formulation in which the adversary learns to reconstruct sensitive inputs, while LCGuard learns transformations that preserve task-relevant semantics and reduce reconstructable information. Empirical evaluations across multiple model families and multi-agent benchmarks show that LCGuard consistently reduces reconstruction-based leakage and attack success rates while maintaining competitive task performance compared to standard KV-sharing baselines.","keywords":["cs.AI","cs.ET","cs.LG","cs.MA"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-05-22T06:00:06.024000Z","dateModified":"2026-05-22T06:00:06.024000Z"}