SAFESHIELD: A Decision-Organization Framework for Deployment-Time Safety of Small Language Models

cs.SE, cs.AI, cs.CR

Submitted: 2026-10-05

Updated: 2026-10-05

Comments: Accepted to the Application Track of IEEE TPS 2026. 12 pages

Code: https://github.com/guardrails-ai/guardrails

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• On-Device Language Models: A Comprehensive Review
• ShieldGemma: Generative AI Content Moderation Based on Gemma
• Constitutional AI: Harmlessness from AI Feedback
• Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties