{"data":{"id":"d028af76-ca71-464f-bfe2-9518bc35e659","title":"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).","solution":"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.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.13696v1","publishedAt":"2026-11-10T07:43:02.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-10T07:43:02.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","confidentiality"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}