| Framework Home | Research Index | Cross-Pillar Governance | AISM | NEXUS | Dashboard |
Current framework context: AI SAFE² v3.1. This research note preserves its original publication date, evidence, and historical framework references. Use current v3.1 normative control and profile documents for implementation or conformance decisions.
ID: RN-2025-005 | Related Control: [P1.T1.5_ADV], [P5.T1.4_ADV] | Status: Verified
Long-Term Memory Poisoning: Unlike immediate prompt injection, MINJA (Memory Injection) attacks target the agent’s long-term storage (Vector DB).
We implement “Cognitive Hygiene” protocols for long-term storage.
All documents destined for RAG/Memory must be scrubbed of “Control Characters” and adversarial patterns before embedding.
Monitoring the vector space for “Clustering Anomalies.” If a new memory chunk sits in a semantic region known for jailbreaks, it is flagged before retrieval.
| Previous research note | Research Index | Next research note |
| Framework Home | Cross-Pillar Governance | NEXUS | Challenge Lab |
AI SAFE² v3.1 | Cyber Strategy Institute