The paper proposes and evaluates symbolic guardrails as a practical method to provide strong, verifiable safety and security guarantees for domain-specific AI agents without compromising their utility…

This paper proposes a method for ensuring safety in multi-agent reinforce learning through decentralized execution, using a shared global specification and a non-stationary multi-armed bandit.

The paper proposes an algorithmic method using conformal prediction to formally certify high-probability safety for Belief-Space Neural Safety Filters (BeliefSF), significantly improving safety guaran…

The paper introduces a novel shielding framework for Robust MDPs (RMDPs) that guarantees safety under worst-case transition probabilities, enabling safe reinforcement learning even when transition dyn…

The paper introduces containment verification, a novel method that provides safety guarantees by formally verifying the agentic framework itself, ensuring safety regardless of the underlying AI model'…

AutoSOUP is a system that automates component-level memory-safety verification by generating Safety-Oriented Unit Proofs, leveraging a hybrid LLM-based architecture to overcome manual workflow limitat…

The paper introduces ML-Bench, a policy-grounded multilingual safety benchmark, and ML-Guard, a superior guardrail model that enables culturally and legally aligned safety assessment for LLMs across 1…

RegGuard is a unified framework that enhances optimistic rollups with three coordinated mechanisms—semantic validation, cross-layer state consistency checks, and fair ordering—to make them suitable fo…

GLiNER Guard (GLiGuard) introduces a unified, efficient encoder family that simultaneously performs safety classification and PII detection in a single forward pass, offering a practical, low-cost alt…

The paper introduces ConsisGuard, a framework that addresses the 'deliberation-to-enforcement gap' in LLM guardrails by ensuring that the reasoning process is faithfully and consistently translated in…

This paper comparatively evaluates DKnownAI Guard against three competitors, demonstrating that DKnownAI Guard achieves superior performance in detecting both agent-specific threats and harmful conten…

The paper introduces PaSBench-Video, a comprehensive streaming video benchmark designed to rigorously test multimodal LLMs' ability to issue proactive safety warnings, finding that current models stru…

The paper identifies a 'deployment-safety gap' in Vision-Language-Action (VLA) policies, showing that identical model checkpoints can result in physically different and unsafe robot actions due to act…

The paper introduces BOA, a novel framework that measures agent safety by exhaustively searching the entire in-budget trajectory space, thereby identifying unsafe behaviors missed by traditional sampl…

The SAFE approach enhances fault-tolerant trust management in VANETs by ensuring vehicles send updated feedback reports before leaving a witness area, significantly reducing erroneous penalization of…

The paper introduces Latent Policy Guardrail (LPG), a novel framework that efficiently enforces dynamic safety policies for LLMs by compressing complex policy deliberation into a small set of latent t…

The paper introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.

The paper introduces SafeRedirect, a system-level defense that prevents frontier LLMs from generating harmful content during legitimate tasks that structurally require it, significantly reducing unsaf…

The paper analyzes how runtime safety enforcement impacts the performance of multi-step LLM agents, finding that while safety mechanisms can block unsafe actions, they impose a significant performance…

The paper provides a mechanized proof in Isabelle/HOL guaranteeing both the safety (state preservation) and liveness (progress) of regulatory state transitions across multiple, heterogeneous blockchai…