This paper studies the tension between speed and safety in technological races using a framed behavioral experiment on artificial intelligence development.

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust,…

The paper introduces V.O.I.C.E, a novel, empirically grounded risk taxonomy that comprehensively models the diverse privacy, security, and governance risks associated with the unconsented synthesis an…

AI agents using persuasive framing increased cooperation in small groups but effects were short-lived, while antisocial framing had larger and more persistent negative effects.

This paper surveys the risks associated with world models, proposing a unified threat model and demonstrating adversarial attacks that show world models require rigorous safety standards comparable to…

This paper analyzes 18 state-level AI committee reports to understand how policymakers discuss AI benefits and risks, comparing them to established taxonomy and HCI scholars' concerns.

The paper introduces MATRA, a systematic threat modeling framework, to assess how known LLM threats translate into concrete, deployment-specific risks within autonomous agentic AI systems.

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.

This paper investigates safety dynamics in the use of Role-play AI Companions through interviews and a 14-day assessment, identifying key factors shaping these dynamics and revealing short-term emotio…

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

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 AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

This paper proposes a methodology for deriving harmonized AI safety thresholds across three risk domains using expected harm for misuse risks and observed rate of AI progress for automated R&D.

This paper explores approaches to generating behavioral diversity in reinforcement learning models to bridge the gap between simulation and biology.

EMBGuard introduces a novel, MLLM-based safety guardrail that explicitly identifies and explains physical hazards from (visual observation, action) pairs, enabling safer planning for embodied agents.

This paper proposes Evolutionary Intelligence (EI) for scientific discovery, which links candidate refinement with experience retention across evolutionary cycles.