English
Related papers

Related papers: The Authorization-Execution Gap Is a Major Safety …

200 papers

Agentic AI systems are deployed with expectations of substantial productivity gains, yet rigorous empirical evidence reveals systematic discrepancies between pre-deployment expectations and post-deployment outcomes. We review controlled…

Software Engineering · Computer Science 2026-02-26 Sebastian Lobentanzer

Load balancing across a networked environment is a monotonous job. Moreover, if the job to be distributed is a constraint satisfying one, the distribution of load demands core intelligence. This paper proposes parallel processing through…

Distributed, Parallel, and Cluster Computing · Computer Science 2011-03-31 M. Shahriar Hossain , M. Muztaba Fuad , Md. Mahbubul Alam Joarder

Agentic AI governance is a critical component of agentic AI infrastructure ensuring that agents follow their owner's communication and interaction policies, and providing protection against attacks from malicious agents. The…

Cryptography and Security · Computer Science 2026-05-13 Matthew D. Laws , Alina Oprea , Cristina Nita-Rotaru

Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reason is that responsibility, despite being widely discussed, remains a subjective and…

Artificial Intelligence · Computer Science 2026-05-19 Jinwei Hu , Xinmiao Huang , Qisong He , Youcheng Sun , Yi Dong , Xiaowei Huang

There is an increasing need for automated support for humans monitoring the activity of distributed teams of cooperating agents, both human and machine. We characterize the domain-independent challenges posed by this problem, and describe…

Multiagent Systems · Computer Science 2011-06-24 P. Berry , T. J. Lee , D. E. Wilkins

Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems work has explored learned runtimes in which computation, memory and I/O migrate into model…

Artificial Intelligence · Computer Science 2026-05-05 Maximiliano Armesto , Christophe Kolb

Recent events surrounding the relationship between frontier AI suppliers and national-security customers have made a structural problem newly visible: once a privately governed model becomes embedded in military workflows, the supplier can…

Computers and Society · Computer Science 2026-04-24 Peng Wei , Wesley Shu

Reasoning over heterogeneous artifacts (PDFs, spreadsheets, slide decks, etc.) increasingly occurs within structured agent workflows that iteratively extract, transform, and reference external information. In these workflows, uncertainty is…

Artificial Intelligence · Computer Science 2026-05-01 Anna Mazhar , Huzaifa Suri , Sainyam Galhotra

As autonomous AI agents increasingly populate the Internet, a novel security challenge arises: "Is this entity an AI agent?" It is a new entity-type verification problem with no established solution. We formalize the problem through a…

Cryptography and Security · Computer Science 2026-03-10 Zuyao Xu , Xiang Li , Fubin Wu , Yuqi Qiu , Lu Sun , FaSheng Miao

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…

Artificial Intelligence · Computer Science 2026-05-29 Benlong Wu , Weiming Zhang , Kejiang Chen , Han Fang , Nenghai Yu

The problem of assigning agents to tasks is a central computational challenge in many multi-agent autonomous systems. However, in the real world, agents are not always perfect and may fail due to a number of reasons. A motivating…

Robotics · Computer Science 2020-07-02 Russell Schwartz , Pratap Tokekar

When an autonomous agent behaves undesirably, including failure to complete a task, it can be difficult to determine whether the behavior is due to a systemic agent error, such as flaws in the model or policy, or an environment error, where…

Artificial Intelligence · Computer Science 2026-01-16 Yashwanthi Anand , Rahil P Mehta , Manish Motwani , Sandhya Saisubramanian

AI agents capable of GUI understanding and Model Context Protocol are increasingly deployed to automate mobile tasks. However, their reliance on over-privileged, static permissions creates a critical vulnerability: instruction injection.…

Cryptography and Security · Computer Science 2025-10-31 Yifeng Cai , Ziming Wang , Zhaomeng Deng , Mengyu Yao , Junlin Liu , Yutao Hu , Ziqi Zhang , Yao Guo , Ding Li

Open-weight large language models (LLMs) unlock huge benefits in innovation, personalization, privacy, and democratization. However, their core advantage - modifiability - opens the door to systemic risks: bad actors can trivially subvert…

Computers and Society · Computer Science 2025-07-17 Ann-Kathrin Dombrowski , Dillon Bowen , Adam Gleave , Chris Cundy

AI systems face a growing number of AI security threats that are increasingly exploited in the real world. Hence, shared AI incident reporting practices are emerging in industry as best practice and as mandated by regulatory requirements.…

Cryptography and Security · Computer Science 2026-05-06 Lukas Bieringer , Sean McGregor , Nicole Nichols , Kevin Paeth , Jochen Stängler , Andreas Wespi , Alexandre Alahi , Kathrin Grosse

This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While…

Cryptography and Security · Computer Science 2026-05-25 Yutong Jin , Zelin Zhang , Zhijin Lyu , Jianbing Ni

As researchers continue to optimize AI agents for more effective task execution within operating systems, they often overlook a critical security concern: the ability of these agents to detect "impostors" within their environment. Through…

Computation and Language · Computer Science 2025-08-07 Yurun Chen , Xavier Hu , Keting Yin , Juncheng Li , Shengyu Zhang

As the industry increasingly adopts agentic AI systems, understanding their unique vulnerabilities becomes critical. Prior research suggests that security flaws at the model level do not fully capture the risks present in agentic…

Artificial Intelligence · Computer Science 2025-09-23 Ilham Wicaksono , Zekun Wu , Rahul Patel , Theo King , Adriano Koshiyama , Philip Treleaven

Failure attribution in multi-agent systems -- pinpointing the exact step where a decisive error occurs -- is a critical yet unsolved challenge. Current methods treat this as a pattern recognition task over long conversation logs, leading to…

Artificial Intelligence · Computer Science 2025-09-24 Alva West , Yixuan Weng , Minjun Zhu , Zhen Lin , Zhiyuan Ning , Yue Zhang

Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…

Machine Learning · Computer Science 2026-04-02 Aengus Lynch