MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
Large language models in medicine
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LLM pipeline with novel attribution algorithm extracts ROS entities, negation status, and body systems from 24 clinical notes at up to 0.952 F1 using open-source models.
citing papers explorer
-
Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
-
A Large Language Model Based Pipeline for Review of Systems Entity Recognition from Clinical Notes
LLM pipeline with novel attribution algorithm extracts ROS entities, negation status, and body systems from 24 clinical notes at up to 0.952 F1 using open-source models.