Cover Image

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Fernandez, Marcelo
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Agent Control Protocol: Admission Control for Agent Actions
by: Fernandez, Marcelo
Published: (2026)

SUDP: Secret-Use Delegation Protocol for Agentic Systems
by: Yu, Xiaohang, et al.
Published: (2026)

Agentic JWT: A Secure Delegation Protocol for Autonomous AI Agents
by: Goswami, Abhishek
Published: (2025)

SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems
by: Patil, KrishnaSaiReddy
Published: (2026)

Not My Agent, Not My Boundary? Elicitation of Personal Privacy Boundaries in AI-Delegated Information Sharing
by: Guo, Bingcan, et al.
Published: (2025)

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
by: Zhuang, Haomin, et al.
Published: (2026)

INVARLLM: LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection
by: Abshari, Danial, et al.
Published: (2024)

Measuring Safety Alignment Effects in Autonomous Security Agents
by: David, Isaac, et al.
Published: (2026)

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
by: Abdelnabi, Sahar, et al.
Published: (2026)

Agent Audit: A Security Analysis System for LLM Agent Applications
by: Zhang, Haiyue, et al.
Published: (2026)

Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems
by: Fernandez, Marcelo
Published: (2026)

Agent Security is a Systems Problem
by: Christodorescu, Mihai, et al.
Published: (2026)

Functional Invariants to Watermark Large Transformers
by: Fernandez, Pierre, et al.
Published: (2023)

HARP: Measuring Harm Amplification in Multi-Agent LLM Systems
by: Rahman, Md Hafizur, et al.
Published: (2026)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
by: Ning, Liang-bo, et al.
Published: (2025)

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
by: Conde, Pedro, et al.
Published: (2026)

Invariant-based Robust Weights Watermark for Large Language Models
by: Guo, Qingxiao, et al.
Published: (2025)

Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures
by: Wang, Suqing, et al.
Published: (2025)

From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
by: Zhang, Xiaolei, et al.
Published: (2026)

You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents
by: Kao, Ching-Yu, et al.
Published: (2026)

Lessons from Penetration Tests on Large-Scale Agent Systems
by: Eykholt, Kevin, et al.
Published: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
by: Feng, Yunhao, et al.
Published: (2026)

Towards Unifying Quantitative Security Benchmarking for Multi Agent Systems
by: Sharma, Gauri, et al.
Published: (2025)

Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems
by: Sharma, Ankur, et al.
Published: (2026)

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
by: Ferrag, Mohamed Amine, et al.
Published: (2025)

Access Controlled Website Interaction for Agentic AI with Delegated Critical Tasks
by: Kim, Sunyoung, et al.
Published: (2026)

Multi-Agent Optimization for Safety Analysis of Cyber-Physical Systems: Position Paper
by: Gürcan, Önder, et al.
Published: (2024)

Context Lineage Assurance for Non-Human Identities in Critical Multi-Agent Systems
by: Malkapuram, Sumana, et al.
Published: (2025)

The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise
by: Lupinacci, Matteo, et al.
Published: (2025)

PiMRef: Detecting and Explaining Ever-evolving Spear Phishing Emails with Knowledge Base Invariants
by: Liu, Ruofan, et al.
Published: (2025)

MultiPhishGuard: An Explainable and Adaptive Multi-Agent LLM System for Phishing Email Detection
by: Xue, Yinuo, et al.
Published: (2025)

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
by: Ai, Zhenxin, et al.
Published: (2026)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
by: Xiang, Chong, et al.
Published: (2026)

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference
by: Xiong, Zixun, et al.
Published: (2026)

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
by: Litvak, Ron
Published: (2026)

LumiMAS: A Comprehensive Framework for Real-Time Monitoring and Enhanced Observability in Multi-Agent Systems
by: Solomon, Ron, et al.
Published: (2025)

D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security
by: Udeshi, Meet, et al.
Published: (2025)

Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems
by: Huang, Yuhang, et al.
Published: (2026)

AgentMark: Utility-Preserving Behavioral Watermarking for Agents
by: Huang, Kaibo, et al.
Published: (2026)

From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems
by: Li, Muyang
Published: (2025)