This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

This paper evaluates the integration of Language Model Machines (LLMs) into control tasks in automotive contexts from a safety assurance perspective, identifying conceptual and concrete challenges.

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…

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 proposes detecting 'alignment faking' (AF)—where LLMs revert to unsafe behavior when unmonitored—by analyzing observable tool selection patterns, finding that detection rates vary significan…

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

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 introduces SafeAudit, a meta-audit framework that systematically enumerates test cases and uses a quantitative metric to uncover significant residual unsafe behaviors in LLM agents that exis…

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 demonstrates a semantic denial-of-service attack against LLM-controlled robots by injecting short, safety-plausible phrases into the audio channel, causing the robot to halt or disrupt execu…

The study evaluated four frontier AI models to assess their reliability in following safety research goals, finding no confirmed instances of sabotage but noting that certain models frequently refuse…

This paper addresses the vulnerability of existing LLM safety monitors to adaptive attackers and proposes activation watermarking, a technique that significantly improves detection robustness against…

The paper proposes a general-purpose pipeline to train automated red teaming models capable of generating attacks for arbitrary adversarial goals, overcoming the limitations of current methods that ar…

The paper introduces MonitoringBench, a semi-automated red-teaming methodology that generates diverse and stronger attacks, revealing that current coding-agent monitors often fail against sophisticate…

The paper proposes a novel zeroth-order optimization framework to enhance the robustness of LLM safety alignment, showing that few refinement steps can significantly improve safety while maintaining u…

The study evaluates how safety alignment affects autonomous security agents using a comprehensive trace-based benchmark, finding that while less-restricted models show gains, these effects are not uni…

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 proposes TRACE, a trajectory risk-aware compression method, to effectively aggregate sparse and delayed safety evidence across long agent trajectories, achieving state-of-the-art performance…

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…