PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models
cs.CL
Submitted: 2026-11-02
Updated: 2026-11-03
Code: https://github.com/Alibaba-AAIG/PGuardhttps:
Terminology
Sources
- kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
- ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
- Are We on the Right Way for Evaluating Large Vision-Language Models?
- Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
- Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
- The Llama 3 Herd of Models
- Segment-Level Coherence for Robust Harmful Intent Probing in LLMs
- SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
- LLM Safety From Within: Detecting Harmful Content with Internal Representations
- Building Production-Ready Probes For Gemini
- HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model
- Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
- YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models
- MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
- GuardReasoner: Towards Reasoning-based LLM Safeguards
- ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior
- Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
- Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
- UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data