中文
相关论文

相关论文: HAICOSYSTEM: An Ecosystem for Sandboxing Safety Ri…

200 篇论文

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

密码学与安全 · 计算机科学 2026-05-27 Kevin Eykholt , Dhilung Kirat , Xiaokui Shu , Jiyong Jang , Frederico Araujo , Ian Molloy

The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk awareness and transparency in risk diagnosis. To introduce…

The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will harm humans via intentional misuse (AI-misuse)…

人工智能 · 计算机科学 2023-05-31 Catalin Mitelut , Ben Smith , Peter Vamplew

As interfaces evolve from static user pathways to dynamic human-AI collaboration, no standard methods exist for selecting appropriate interface patterns based on user needs and task complexity. Existing frameworks only provide guiding…

人机交互 · 计算机科学 2026-02-27 Shruthi Andru , Shrut Kirti Saksena

As Artificial Intelligence (AI) technologies continue to advance, protecting human autonomy and promoting ethical decision-making are essential to fostering trust and accountability. Human agency (the capacity of individuals to make…

计算机与社会 · 计算机科学 2025-10-13 Laxmiraju Kandikatla , Branislav Radeljic

Recent advances in large language models (LLMs) have enabled the development of AI agents that exhibit increasingly human-like behaviors, including planning, adaptation, and social dynamics across diverse, interactive, and open-ended…

Recent advancements in the field of Artificial Intelligence (AI) establish the basis to address challenging tasks. However, with the integration of AI, new risks arise. Therefore, to benefit from its advantages, it is essential to…

机器学习 · 计算机科学 2024-12-20 Ronald Schnitzer , Andreas Hapfelmeier , Sven Gaube , Sonja Zillner

Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process. Recently, substantial evidences…

This chapter formulates seven lessons for preventing harm in artificial intelligence (AI) systems based on insights from the field of system safety for software-based automation in safety-critical domains. New applications of AI across…

系统与控制 · 电气工程与系统科学 2022-02-21 Roel I. J. Dobbe

This paper examines the responsible integration of artificial intelligence (AI) in human services organizations (HSOs), proposing a nuanced framework for evaluating AI applications across multiple dimensions of risk. The authors argue that…

计算机与社会 · 计算机科学 2025-01-22 Brian E. Perron , Lauri Goldkind , Zia Qi , Bryan G. Victor

This paper explores the growing presence of emotionally responsive artificial intelligence through a critical and interdisciplinary lens. Bringing together the voices of early-career researchers from multiple fields, it explores how AI…

Given the exponential advancement in AI technologies and the potential escalation of harmful effects from recommendation systems, it is crucial to simulate and evaluate these effects early on. Doing so can help prevent possible damage to…

社会与信息网络 · 计算机科学 2025-02-04 Ljubisa Bojic , Zorica Dodevska , Yashar Deldjoo , Nenad Pantelic

Balancing user agency and system automation is essential for effective human-AI interactions. Fully automated systems can deliver efficiency but risk undermining usability and user autonomy, while purely manual tools are often inefficient…

人机交互 · 计算机科学 2025-02-20 Thomas Langerak

The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect a community's values), which current systems fall short on.…

As generative AI enters enterprise workflows, ensuring compliance with legal, ethical, and reputational standards becomes a pressing challenge. In beauty tech, where biometric and personal data are central, traditional reviews are often…

人机交互 · 计算机科学 2025-11-19 Junwei Li , Wenqing Wang , Huiliu Mao , Jiazhe Ni , Zeyu Xiong

Collaborative AI experimentation in industry and academia requires environments that support rapid trials while maintaining controlled access, organisational isolation, and traceable workflows. Although interest in AI sandboxes is…

Large Language Models (LLMs) enable unprecedented social science experimentation by creating controlled hybrid human-AI environments. We introduce Epitome (www.epitome-ai.com), an open experimental platform that operationalizes this…

计算机与社会 · 计算机科学 2025-12-25 Jingjing Qu , Kejia Hu , Jun Zhu , Yulei Ye , Wenhao Li , Teng Wang , Zhiyun Chen , Chaochao Lu , Aimin Zhou , Xiangfeng Wang , Xia Hu , James Evans

As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…

计算机与社会 · 计算机科学 2025-08-21 Carson Ezell , Xavier Roberts-Gaal , Alan Chan

AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…

计算机与社会 · 计算机科学 2026-02-10 Cheng Yu , Severin Engelmann , Ruoxuan Cao , Dalia Ali , Orestis Papakyriakopoulos