Memory poisoning

Concept

Memory poisoning is an attack in which malicious instructions are planted in content an AI agent stores in its persistent memory, so they resurface and influence later decisions.

Title graphic: Memory poisoning (Concept)

Type	Concept

Articles about Memory poisoning (2)

거버넌스 격차 해소: AI 감독 관리를 위한 모범 사례
2026-08-12 · Mirko Peters
조직들이 자율형 인공지능을 일상 업무에 서둘러 도입하면서, 앞으로 중대한 과제가 떠오르고 있습니다. 바로 거버넌스 격차입니다. 국가와 국제 규제가 빠른 기술 발전을 따라가지 못하는 가운데, 현재 많은 프레임워크는 자발적 준수에 크게 의존하고 있습니다. 그로 인해 특히 에이전트 권한, 무단 접근, 의무적인 사람의 감독 부재
Bridging the Governance Gap: Best Practices for Managing AI Oversight
2026-08-12 · Mirko Peters
As organizations rush to integrate autonomous artificial intelligence into their daily workflows, a critical challenge looms on the horizon: the governance gap. Whi…

Glossary

Community wiki

Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.

Experts and companies for this topic

Nobody has listed this topic yet. Add it to your profile.

Sources

Feed for this topic (RSS): entity/memory-poisoning/feed.xml
Articles on this topic: 2

Maintained by Mirko Peters (Microsoft MVP) · Last updated: 2026-11-03