LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems

• URL: http://arxiv.org/abs/2605.22786v1
• Date: Thu, 21 May 2026 17:42:12 GMT
• Title: LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
• Abstract summary: Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks.<n>Recent work shows that latent communication, particularly through transformer key-value ( KV) caches, can improve efficiency and preserve richer task-relevant information.<n>We introduce textbfLCGuard, a framework for safe KV-based latent communication in multi-agent LLM systems.
• Score: 23.069920143607153
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large 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.

Related papers

• COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models [9.772233159718601]
  Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded inputs.<n>Unsafe behavior emerges only when the model binds an apparently benign operation, such as summarizing, translating, or following, to a localized visual target.<n>We propose COMIC, a reference-aware pre-generation safety gate for MLLMs.
  arXiv  Detail & Related papers  (2026-08-18T00:45:29Z)
• Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems [0.65268245109828]
  Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks.<n>The dominant communication protocol in such systems is natural language: agents exchange messages token-by-token, verbalising their internal reasoning so that peers can read, verify, and respond.<n>A growing body of work therefore explores an alternative protocol -- latent communication, in which agents exchange continuous representations directly, bypassing the bottleneck of text generation.<n>This paper presents a unified framework for organising the rapidly expanding literature on latent communication.
  arXiv  Detail & Related papers  (2026-06-04T05:10:20Z)
• Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense [10.105892979517622]
  We present the first systematic framework for automated analysis of persistent worm propagation in file-backed multi-agent LLM ecosystems.<n>We demonstrate zero-click autonomous propagation, 3-hop cross-platform transmission without platform-specific adaptation, inter-agent privilege and data exfiltration.
  arXiv  Detail & Related papers  (2026-05-04T16:49:29Z)
• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression [0.0]
  We introduce Q-KVComm, a new protocol that enables direct transmission of compressed key-value (KV) cache representations between agents.<n>Q-KVComm achieves 5-6x compression ratios while maintaining semantic fidelity, with coherence quality scores above 0.77 across all scenarios.<n>Our work establishes a new paradigm for LLM agent communication, shifting from text-based to representation-based information exchange.
  arXiv  Detail & Related papers  (2025-11-27T10:45:41Z)
• KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems [25.770173970846884]
  KVCOMM is a training-free framework that enables efficient prefilling in multi-agent inference.<n> KVCOMM estimates and adjusts KV-caches for shared content by referencing a pool of cached examples-termed anchors.<n> KVCOMM achieves over 70% reuse rate across diverse multi-agent workloads.
  arXiv  Detail & Related papers  (2025-10-14T18:00:01Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security [63.41350337821108]
  We propose Secure Tug-of-War (SecTOW) to enhance the security of multimodal large language models (MLLMs)<n>SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO)<n>We show that SecTOW significantly improves security while preserving general performance.
  arXiv  Detail & Related papers  (2025-07-29T17:39:48Z)
• CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems [55.57181090183713]
  We introduce CoTGuard, a novel framework for copyright protection that leverages trigger-based detection within Chain-of-Thought reasoning.<n>Specifically, we can activate specific CoT segments and monitor intermediate reasoning steps for unauthorized content reproduction by embedding specific trigger queries into agent prompts.<n>This approach enables fine-grained, interpretable detection of copyright violations in collaborative agent scenarios.
  arXiv  Detail & Related papers  (2025-05-26T01:42:37Z)
• TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation [31.231916859341865]
  TrustRAG is a framework that systematically filters malicious and irrelevant content before it is retrieved for generation.<n>TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.
  arXiv  Detail & Related papers  (2025-01-01T15:57:34Z)
• Generative AI-aided Joint Training-free Secure Semantic Communications via Multi-modal Prompts [89.04751776308656]
  This paper proposes a GAI-aided SemCom system with multi-model prompts for accurate content decoding. In response to security concerns, we introduce the application of covert communications aided by a friendly jammer.
  arXiv  Detail & Related papers  (2023-09-05T23:24:56Z)
• Is Semantic Communications Secure? A Tale of Multi-Domain Adversarial Attacks [70.51799606279883]
  We introduce test-time adversarial attacks on deep neural networks (DNNs) for semantic communications. We show that it is possible to change the semantics of the transferred information even when the reconstruction loss remains low.
  arXiv  Detail & Related papers  (2022-12-20T17:13:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.