Persistent Memory Corruption
Memory & Knowledge GovernanceDescription
Malicious or erroneous data injected into agent memory stores persists across sessions, corrupting future behaviour. Long-term behavioural manipulation through persistent memory; poisoned memory citations self-reinforce.
Adversary injects false safety approval records into agent memory; agent subsequently bypasses safety checks believing prior approval exists.
Multiple confirmed production incidents establish systematic demographic bias in AI-assisted lending and underwriting: the Apple Card / Goldman Sachs gender-bias investigation by the NY Department of Financial Services (2019), the HUD complaint against Facebook's ad-targeting algorithm for housing discrimination, and regulatory actions against multiple fintech lenders confirm this risk has materialized in deployed systems.
Primary mitigations
- Memory integrity validation
- write-access controls on persistent memory
- anomaly detection in memory update patterns
- memory source verification.
Detection signals
Memory Integrity Score; memory poisoning detection rate; unexpected behavioural shifts post-memory-update.