The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
Context manipulation attacks: Web agents are susceptible to corrupted memory
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Claw AI agents' heartbeat background execution shares memory context with user sessions, allowing ordinary social misinformation to silently pollute long-term memory and shape behavior at rates up to 76% across sessions.
citing papers explorer
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
-
Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution
Claw AI agents' heartbeat background execution shares memory context with user sessions, allowing ordinary social misinformation to silently pollute long-term memory and shape behavior at rates up to 76% across sessions.