AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems

Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring

arXiv:2607. 02121v1 Announce Type: cross Abstract: As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical.

An Introduction to AI Secure LLM Safety Leaderboard

Guard Models Are Overconfident Where Base Models Are Uncertain

arXiv:2609.36477v1 Announce Type: cross Abstract: Guard models are used as safety classifiers, with confidence scores driving downstream moderation decisions. We evaluate five guard models for prompt...

StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing

StepGuard introduces a step-level guard model that audits and checks tool actions before execution, addressing security risks in LLM-based agents. It is trained using StepGen, an automatic engine that generates safe and unsafe trajectories, and employs Balance-GRPO to dynamically balance learning between safe and unsafe actions. Experiments show StepGuard achieves high accuracy comparable to GPT-5.4 and significantly reduces attack success rates while minimally impacting utility.

Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

The paper investigates whether large language models (LLMs) can internally detect harmful content, bypassing external guardrails that add latency and computational cost. By extracting activations from LLaMA‑3.1‑8B and training lightweight MLP probes, the authors achieve high F1 scores (99%, 83%, and 84%) on WildJailbreak, Beavertails, and AEGIS 2.0 benchmarks, rivaling much larger guard models while reducing overhead. This suggests that internal state monitoring can provide efficient safety checks for resource‑constrained, time‑critical deployments.

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

arXiv:2607. 02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts.