相关论文: A Trajectory-Based Safety Audit of Clawdbot (OpenC…
The World Action Model (WAM) can jointly predict future world states and actions, exhibiting stronger physical manipulation capabilities compared with traditional models. Such powerful physical interaction ability is a double-edged sword:…
The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
AI impact assessments often stress near-term risks because human judgment degrades over longer horizons, exemplifying the Collingridge dilemma: foresight is most needed when knowledge is scarcest. To address long-term systemic risks, we…
In recent years, chatbots have gained widespread adoption thanks to their ability to assist users at any time and across diverse domains. However, the lack of large-scale curated datasets limits research on their quality and reliability.…
AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and…
In today's contemporary digital landscape, chatbots have become indispensable tools across various sectors, streamlining customer service, providing personal assistance, automating routine tasks, and offering health advice. However, their…
Teleoperated quadruped robots are increasingly deployed in safety-critical missions -- industrial inspection, military reconnaissance, and emergency response -- yet the security of their communication and control infrastructure remains…
In chess, zugzwang describes a scenario where any move worsens the player's position. Organizations face a similar dilemma right now at the intersection of artificial intelligence (AI) and cybersecurity. AI adoption creates an inevitable…
The rapid proliferation of large language models (LLMs) in applications targeting children and adolescents necessitates a fundamental reassessment of prevailing AI safety frameworks, which are largely tailored to adult users and neglect the…
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…
Conversational AI chatbots are transforming industries by streamlining customer service, automating transactions, and enhancing user engagement. However, evaluating these systems remains a challenge, particularly in financial services,…
AI chatbots designed as emotional companions blur the boundaries between interpersonal intimacy and institutional software, creating a complex, multi-dimensional privacy environment. Drawing on Communication Privacy Management theory and…
Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language…
We present an overview of recently developed data-driven tools for safety analysis of autonomous vehicles and advanced driver assist systems. The core algorithms combine model-based, hybrid system reachability analysis with sensitivity…
Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…
Autonomous systems with cognitive features are on their way into the market. Within complex environments, they promise to implement complex and goal oriented behavior even in a safety related context. This behavior is based on a certain…
Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…
Trust is essential for our interactions with others but also with artificial intelligence (AI) based systems. To understand whether a user trusts an AI, researchers need reliable measurement tools. However, currently discussed markers…
Trajectory prediction is one of the key components of the autonomous driving software stack. Accurate prediction for the future movement of surrounding traffic participants is an important prerequisite for ensuring the driving efficiency…