On Private Knowledge Retrieval and Private Inference for secure multi-agent systems

Summary

This research paper examines memory poisoning attacks on the semantic memory of LLM-based agents in multi-agent systems, where malicious agents can alter an agent's knowledge and behavior. The authors propose private knowledge retrieval and private inference, with a signature system on the knowledge base to block undesired manipulation. Each agent runs a local Prolog-like inference system over Horn clauses that queries an externally signed knowledge base privately. The authors provide Python implementations using k-anonymity and information-theoretical privacy (IT-PIR).

Mitigation

The paper proposes a signature system in the knowledge base to prevent undesired manipulation, building security by design into the construction of the semantic memory, with private access to the externally signed knowledge base via k-anonymity or IT-PIR.

Related items

• HighCVE-2026-63651: LiveDocs is a primary-source-first documentation for AI agents. Prior to version 0.7.0, fetch_docs and introspect…Similar attack · NVD/CVE Database
• HighCVE-2026-125271 - AWS API MCP Server Security Policy Bypass via Incorrect Operation Name NormalizationSimilar attack · AWS Security Bulletins
• InfoLocation Matters: Sparse Latent-Variance Attacks for Face Privacy against Diffusion PersonalizationSimilar attack · Arxiv (cs.RO + cs.CV security)
• MediumCVE-2026-83953 GitHub Copilot for Jetbrains Information Disclosure VulnerabilitySimilar attack · MSRC Security Update Guide
• HighGHSA-ghwv-vrp2-2975: Cocos AI Intra-handshake attested TLS implementation is vulnerable to TOCTOU AttacksSimilar attack · GitHub Advisory Database