ToolMinimize: Auditing and Rewriting LLM Agent Tool Calls to Minimize Privacy Exposure
cs.CR, cs.SE
Submitted: 2026-08-25
Updated: 2026-08-25
Terminology
Sources
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Tool Learning with Large Language Models: A Survey
- AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
- Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
- Progent: Securing AI Agents with Privilege Control
- Securing AI Agents with Information-Flow Control
- RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
- Defeating Prompt Injections by Design
- AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
- Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
- AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems
- The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
- MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
- Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
- The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
- Privacy Auditing of Large Language Models
- Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
- IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
- PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs