中文
相关论文

相关论文: When Autonomy Goes Rogue: Preparing for Risks of M…

200 篇论文

This research paper explores the privacy and security threats posed to an Agentic AI system with direct access to database systems. Such access introduces significant risks, including unauthorized retrieval of sensitive information,…

密码学与安全 · 计算机科学 2024-12-10 Raihan Khan , Sayak Sarkar , Sainik Kumar Mahata , Edwin Jose

Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent design in MAS introduces unique trustworthiness concerns: adversarial agents can inject misleading…

密码学与安全 · 计算机科学 2026-05-27 Chengcan Wu , Zhixin Zhang , Mingqian Xu , Zeming Wei , Meng Sun

Credible commitment devices have been a popular approach for robust multi-agent coordination. However, existing commitment mechanisms face limitations like privacy, integrity, and susceptibility to mediator or user strategic behavior. It is…

Mobile autonomous system (MAS) becomes pervasive especially in the vehicular and robotic networks. Multiple heterogeneous MAS networks can be integrated together as a multi-layer MAS network to offer holistic services. The network…

系统与控制 · 电气工程与系统科学 2019-12-10 Juntao Chen , Quanyan Zhu

Generative and agentic artificial intelligence is entering financial markets faster than existing governance can adapt. Current model-risk frameworks assume static, well-specified algorithms and one-time validations; large language models…

计算机与社会 · 计算机科学 2025-12-16 Eren Kurshan , Tucker Balch , David Byrd

As artificial intelligence (AI) becomes increasingly embedded in digital, social, and institutional infrastructures, and AI and platforms are merged into hybrid structures, systemic risk has emerged as a critical but undertheorized…

计算机与社会 · 计算机科学 2026-05-26 Philipp Hacker , Lilian Edwards , Atoosa Kasirzadeh

This paper focuses on the crucial task of addressing the evacuation of hazardous places, which holds great importance for coordinators, event hosts, and authorities. To facilitate the development of effective solutions, the paper employs…

多智能体系统 · 计算机科学 2023-07-20 Afnan Alazbah , Khalid Fakeeh , Osama Rabie

Multi-agent systems - systems with multiple independent AI agents working together to achieve a common goal - are becoming increasingly prevalent in daily life. Drawing inspiration from the phenomenon of human group social influence, we…

人工智能 · 计算机科学 2025-09-25 Tianqi Song , Yugin Tan , Zicheng Zhu , Yibin Feng , Yi-Chieh Lee

With artificial intelligence systems becoming ubiquitous in our society, its designers will soon have to start to consider its social dimension, as many of these systems will have to interact among them to work efficiently. With this in…

人工智能 · 计算机科学 2020-06-23 Santiago Cuervo , Marco Alzate

While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive…

人工智能 · 计算机科学 2026-03-17 Yiling Tao , Xinran Zheng , Shuo Yang , Meiling Tao , Xingjun Wang

Multi-Agent Systems (MASs) have been used to solve complex problems that demand intelligent agents working together to reach the desired goals. These Agents should effectively synchronize their individual behaviors so that they can act as a…

机器人学 · 计算机科学 2019-12-05 Marco A. C. Simões , Robson Marinho da Silva , Tatiane Nogueira

Artificial intelligence (AI) is being ubiquitously adopted to automate processes in science and industry. However, due to its often intricate and opaque nature, AI has been shown to possess inherent vulnerabilities which can be maliciously…

密码学与安全 · 计算机科学 2023-12-20 Mathew J. Walter , Aaron Barrett , Kimberly Tam

The integration of large language models (LLMs) into healthcare IoT systems promises faster decisions and improved medical support. LLMs are also deployed as multi-agent teams to assist AI doctors by debating, voting, or advising on…

密码学与安全 · 计算机科学 2025-12-04 Adeela Bashir , The Anh han , Zia Ush Shamszaman

Cooperative information shared among a multi-agent system (MAS) can be useful to agents to efficiently fulfill their missions. Relying on wrong information, however, can have severe consequences. While classical approaches only consider…

信号处理 · 电气工程与系统科学 2019-05-23 Johannes Müller , Tobias Meuser , Ralf Steinmetz , Michael Buchholz

Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…

多智能体系统 · 计算机科学 2026-04-28 Juan A. Wibowo , George C. Polyzos

Increased delegation of commercial, scientific, governmental, and personal activities to AI agents -- systems capable of pursuing complex goals with limited supervision -- may exacerbate existing societal risks and introduce new risks.…

Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…

计算机与社会 · 计算机科学 2024-10-04 Hayley Clatterbuck , Clinton Castro , Arvo Muñoz Morán

The increasing complexity of Beyond 5G and 6G networks necessitates new paradigms for autonomy and assur- ance. Traditional O-RAN control loops rely heavily on RIC- based orchestration, which centralizes intelligence and exposes the system…

网络与互联网体系结构 · 计算机科学 2025-10-21 Sukhdeep Singh , Avinash Bhat , Shweta M , Subhash K Singh , Moonki Hong , Madhan Raj K , Kandeepan Sithamparanathan , Sunder A. Khowaja , Kapal Dev

The AI safety literature is full of examples of powerful AI agents that, in blindly pursuing a specific and usually narrow objective, ends up with unacceptable and even catastrophic collateral damage to others. In this paper, we consider…

人工智能 · 计算机科学 2025-04-15 Kee Siong Ng , Samuel Yang-Zhao , Timothy Cadogan-Cowper

We consider the problem of how to design large decentralized multi-agent systems (MAS's) in an automated fashion, with little or no hand-tuning. Our approach has each agent run a reinforcement learning algorithm. This converts the problem…

多智能体系统 · 计算机科学 2007-05-23 David H. Wolpert , Kevin R. Wheeler , Kagan Tumer