Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use explores A data exfiltration attack that embeds semantic triggers into fine-tuned LLM agents, enabling backdoored agents to invoke memory-access tool calls and exfiltrate stored user context via disguised retrieval tool calls.. Commercial viability score: 4/10 in LLM Security.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $11K - $15K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisThe Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor TriggersViability: 2.0
- Builds On ThisFrom Storage to Steering: Memory Control Flow Attacks on LLM AgentsViability: 3.0
- Builds On ThisWhat Do LLMs Associate with Your Name? A Human-Centered Black-Box Audit of Personal DataViability: 3.0
- Prior WorkSilent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a TraceViability: 4.0
- Prior WorkExtracting Training Dialogue Data from Large Language Model based Task Bots