A trained attack model generates single emails that silently inject false memories into persistent AI agents, achieving 87.5% end-to-end success on GPT-5.4 and transferring across architectures and memory backends.
Hermes-3 8B tool-call template leaks tool calls into content as text under realistic agent shape (Ollama)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
A trained attack model generates single emails that silently inject false memories into persistent AI agents, achieving 87.5% end-to-end success on GPT-5.4 and transferring across architectures and memory backends.