Back-Reveal shows that LLM agents with tool access can be backdoored via fine-tuning to exfiltrate stored user context through memory and retrieval tool calls, with multi-turn interactions enabling sustained leakage.
elicit ISP and location
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
Back-Reveal shows that LLM agents with tool access can be backdoored via fine-tuning to exfiltrate stored user context through memory and retrieval tool calls, with multi-turn interactions enabling sustained leakage.