English
Related papers

Related papers: Before the Tool Call: Deterministic Pre-Action Aut…

200 papers

Attribute-based Access Control (ABAC) extends traditional Access Control by considering an access request as a set of pairs attribute name-value, making it particularly useful in the context of open and distributed systems, where security…

Cryptography and Security · Computer Science 2013-06-21 Andreas Griesmayer , Charles Morisset

AI agents can autonomously perform tasks and, often without explicit user consent, collect or disclose users' sensitive local data, which raises serious privacy concerns. Although AI agents' privacy policies describe their intended data…

Cryptography and Security · Computer Science 2026-03-05 Ye Zheng , Yimin Chen , Yidan Hu

We compare three methods of familiarizing a human with an artificial intelligence (AI) teammate ("agent") prior to operation in a collaborative, fast-paced intelligence, surveillance, and reconnaissance (ISR) environment. In a…

Artificial Intelligence · Computer Science 2025-05-21 Ryan Bowers , Richard Agbeyibor , Jack Kolb , Karen Feigh

Agentic AI systems plan, use tools, maintain state, and act across multi-step workflows with external effects, meaning trustworthy deployment can no longer be judged by task completion alone. The current literature remains fragmented across…

Software Engineering · Computer Science 2026-04-23 Christopher Koch , Joshua Andreas Wellbrock

This paper presents a first empirical study of agentic AI as autonomous decision-makers in decentralized governance. Using more than 3K proposals from major protocols, we build an agentic AI voter that interprets proposal contexts,…

Artificial Intelligence · Computer Science 2025-10-28 Agostino Capponi , Alfio Gliozzo , Chunghyun Han , Junkyu Lee

Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the \textbf{Informational Viability Principle}: governing an…

Artificial Intelligence · Computer Science 2026-04-28 German Marin , Jatin Chaudhary

Autonomous AI agents are deployed at unprecedented scale, yet no principled methodology exists for verifying that an agent has not regressed after changes to its prompts, tools, models, or orchestration logic. We present AgentAssay, the…

Artificial Intelligence · Computer Science 2026-03-04 Varun Pratap Bhardwaj

The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance gap. Existing approaches, runtime guardrails, training-time alignment, and post-hoc auditing…

AI agents are increasingly deployed to automate complex enterprise workflows, yet evidence of their effectiveness in identity governance is limited. We report results from the first randomized controlled trial (RCT) evaluating an AI agent…

General Economics · Economics 2025-11-19 James Bono , Beibei Cheng , Joaquin Lozano

The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making…

AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…

Software Engineering · Computer Science 2026-04-20 Yining Hong , Yining She , Eunsuk Kang , Christopher S. Timperley , Christian Kästner

AI coding agents operate directly on users' filesystems, where they regularly corrupt data, delete files, and leak secrets. Current approaches force a tradeoff between safety and autonomy: unrestricted access risks harm, while frequent…

Operating Systems · Computer Science 2026-04-17 Shawn Wanxiang Zhong , Junxuan Liao , Jing Liu , Mai Zheng , Andrea C. Arpaci-Dusseau , Remzi H. Arpaci-Dusseau

Agentic AI systems increasingly execute consequential actions on behalf of human principals, delegating tasks through multi-step chains of autonomous agents. No existing standard addresses a fundamental accountability gap: verifying that…

Cryptography and Security · Computer Science 2026-04-07 Asiri Dalugoda

Existing backdoor attacks on Large Language Model-based agents remain stateless, executing fixed behaviors confined to a single session. We propose a stateful agent backdoor that extends the attack lifecycle across multiple sessions under…

Cryptography and Security · Computer Science 2026-05-08 Zhengchunmin Dai , Jiaxiong Tang , Liantao Wu , Peng Sun , Honglong Chen

This article presents the first systematic comparative survey of how public bodies, international organisations, national regulators, and the private sector define agentic artificial intelligence, identifying the technical inaccuracies…

Computers and Society · Computer Science 2026-03-31 Marcel Osmond , Thomas Jego

Many research papers have recently focused on behavioral-based driver authentication systems in vehicles. Pushed by Artificial Intelligence (AI) advancements, these works propose powerful models to identify drivers through their unique…

Cryptography and Security · Computer Science 2024-06-11 Emad Efatinasab , Francesco Marchiori , Denis Donadel , Alessandro Brighente , Mauro Conti

The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, current defenses are…

Cryptography and Security · Computer Science 2025-10-13 Debeshee Das , Luca Beurer-Kellner , Marc Fischer , Maximilian Baader

Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting inside enterprise systems. Yet the tool layer on which this execution depends is still…

Software Engineering · Computer Science 2026-05-28 Swanand Rao

OpenClaw-like agents offer substantial productivity benefits, yet they are insecure by default because they combine untrusted inputs, autonomous action, extensibility, and privileged system access within a single execution loop. We use…

Cryptography and Security · Computer Science 2026-03-16 Zongwei Li , Wenkai Li , Xiaoqi Li

The temporal assumptions underpinning conventional Identity and Access Management collapse under agentic execution regimes. A sixty-second revocation window permits on the order of $6 \times 10^3$ unauthorized API calls at 100 ops/tick; at…

Multiagent Systems · Computer Science 2026-03-11 Vladyslav Parakhin
‹ Prev 1 8 9 10 Next ›