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