PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding Agents
Kyutae Park, Jungwon Kim, Daeyeol Shim
cs.CR, cs.SE
Submitted: 2026-08-03
Comments: This paper is being withdrawn because it was submitted prior to completion of a required institutional review process. The authors intend to resubmit after the review is complete
Code: https://github.com/microsoft/presidio
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Evaluating Large Language Models Trained on Code
- WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Ignore Previous Prompt: Attack Techniques For Language Models
- Pr$\epsilon\epsilon$mpt: Sanitizing Sensitive Prompts for LLMs
- Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
- Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- ShieldGemma: Generative AI Content Moderation Based on Gemma
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
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills