AI Agent Security

Follow this topic Ask about this topic

Momentum

43 papers in the last four weeks, up 258% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 311

All topics

A Theory of Least Autonomy in AI
Jul 3, 2026Christophe PariselAI Agent Security AI Agent Governance
CONTRA: Red-Teaming Configurations of Personalizable Agents
Jul 3, 2026Jonathan Nöther, Adish Singla, Goran RadanovicLLM Red Teaming AI Agent Security
Max Planck Institute for Software Systems, Germany
Distributed Attacks in Persistent-State AI Control
Jul 2, 2026Josh Hills, Ida Caspary, Asa Cooper SticklandAI Agent Security AI Agent Security Benchmarks
1Constellation Astra Fellowship · 2Imperial College London · 3UK AI Security Institute
ElephantAgent: Contextual State Continuity in Agentic Systems
Jul 2, 2026Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4Adversarial Attacks AI Agent Security
AI Security Lab · Beijing, China
Janus: a Playground for User-Involved Agentic Permission Management
Jul 1, 2026Natalie Grace Brigham, Eugene Bagdasarian, Tadayoshi Kohno +1AI Agent Security Human-AI Decision Making
University of Washington · University of Massachusetts Amherst · Georgetown University
A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems
Jun 30, 2026Seyed Bagher Hashemi Natanzi, Bo TangAI Agent Security LLM Security
Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
Jun 29, 2026Peizhi Niu, Wenjie Qu, Shangding Gu +14AI Agent Security LLM Agent Security
UIUC · NUS · UC Berkeley +8
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Jun 26, 2026Bo Shen, Lifeng Chang, Tianyuan Wei +7AI Agent Security AI Agent Monitoring
Novo Ordo for AI
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
Jun 24, 2026Seth Dobrin, Łukasz ChmielAI Alignment AI Agent Security
ARYA Labs PBC
Can Trustless Agents Be Trusted? An Empirical Study of the ERC-8004 Decentralized AI Agent Ecosystem
Jun 24, 2026Xihan Xiong, Zelin Li, Wei Wei +3Cybersecurity AI Agent Security
XIHAN XIONG, Imperial College London, UK · ZELIN LI, Ohio State University, USA · WEI WEI, University of Bristol, UK +3
AI Snitches Get Glitches: Towards Evading Agentic Surveillance
Jun 24, 2026Hyejun Jeong, Dzung Pham, Amir Houmansadr +1AI Agent Security AI Agent Security Benchmarks
University of Massachusetts Amherst
Red-Teaming the Agentic Red-Team
Jun 23, 2026Dario Pasquini, Michal Bazyli, Taras Fedynyshyn +1Software Security AI Agent Security
Cracken · Information Protection Department, Lviv Polytechnic National University, Lviv, 79013, Ukraine
RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems
Jun 22, 2026Yarin Yerushalmi Levi, Roy Betser, Amit Giloni +5AI Agent Security AI Agent Security Benchmarks
1Fujitsu Research of Europe (FRE) · 2Fujitsu Research of India Pvt. Ltd. (FRIPL)
Cryptographic certificates of validity for trustworthy AI
Jun 22, 2026Murdoch J. GabbayAI Agent Security AI Agent Governance
Heriot-Watt University, Edinburgh, UK
AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction
Jun 22, 2026Shanhui Zhao, Jiacheng Liu, Guohong Liu +13Computer-Use Agents AI Agent Security
Tsinghua University · Peking University · The University of Hong Kong
Intent-Governed Tool Authorization for AI Agents
Jun 22, 2026Genliang Zhu, Chu WangAI Agent Security AI Agent Governance
Accentrust · Georgia Institute of Technology · University of Illinois Urbana-Champaign
Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents
Jun 21, 2026Igor Santos-GrueiroCoding Agents AI Agent Security
International University of La Rioja
AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems
Jun 20, 2026Srimonti Dutta, Akshata Kishore MoharirAI Risk Management AI Agent Auditing
WAI USA Research Labs · WAI USA · Austin, USA +1
Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
Jun 19, 2026Kerri Prinos, Lilianne Brush, Cameron DentonCybersecurity AI Agent Security
Horizon3.ai, San Francisco, CA, 94111, USA
Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents
Jun 18, 2026Dayeon Kang, Hyejun Jeong, Jade Sheffey +2AI Agent Security Web Agents
UMass Amherst
Sovereign Execution Broker: Enforcing Certificate-Bound Authority in Agentic Control Planes
Jun 18, 2026Jun He, Deying YuAI Agent Security Capability-Based Security
Efficient and Sound Probabilistic Verification for AI Agents
Jun 18, 2026Alaia Solko-Breslin, Pramod Kaushik Mudrakarta, Mihai Christodorescu +2AI Agent Security AI Agent Monitoring
Google DeepMind · Google · University of Wisconsin–Madison
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
Jun 18, 2026Reza Soosahabi, Vivek NamsaniAdversarial Robustness Jailbreak Attacks
Application & Threat Intelligence Research Center Keysight Technologies Inc., USA
Deontic Policies for Runtime Governance of Agentic AI Systems
Jun 17, 2026Anupam Joshi, Tim Finin, Karuna Pande Joshi +1AI Agent Security AI Agent Governance
CSEE Department UMBC Baltimore, MD, USA · Center for AI UMBC Baltimore, MD, USA · Information Systems Department UMBC Baltimore, MD, USA +1
GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
Jun 17, 2026Zhe Ren, Yibo Yang, Yimeng Chen +7LLM Agent Memory AI Agent Security
School of Artificial Intelligence, Jilin University · 2Shanghai Jiao Tong University · 3King Abdullah University of Science and Technology (KAUST) +2
Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework
Jun 16, 2026Petar Radanliev, Omar Santos, Carsten Maple +1Cybersecurity Software Security
Department of Computer Sciences, University of Oxford, Wolfson Building, Parks Rd, Oxford OX1 3QG · The Alan Turing Institute, British Library, 96 Euston Rd., London NW1 2DB · Cisco Systems, RTP, North Carolina, United States +2
Human-on-the-Bridge: Scalable Evaluation for AI Agents
Jun 15, 2026Fouad BousetouaneAI Agent Reliability AI Agent Evaluation
The University of Chicago, USA
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
Jun 15, 2026Yimeng Chen, Zhe Ren, Firas Laakom +3LLM Agent Evaluation AI Agent Security
Center of Excellence for Generative AI, KAUST · 2Jilin University · 3Zhejiang University +2
SoK: Security and Privacy of Foundation-Model-Powered Robots
Jun 15, 2026Xueluan Gong, Chen Chen, Jinxin Liu +2Robot Foundation Models AI Agent Security
College of Computing and Data Science, Nanyang Technological University, Singapore · School of Cyber Science and Engineering, Wuhan University, China
One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents
Jun 14, 2026Chuyang Chen, Zhiqiang LinAI Agent Security LLM Agent Security
The Ohio State University

Jul 3, 2026, cs.AIJ/K move · Enter open · S save

A Theory of Least Autonomy in AI

Christophe Parisel

AI Agent Security AI Agent Governance Access Control Multi-Agent System Security

Open paper AskPDF arXiv

Least privilege, the principle that an identity should hold only the permissions strictly required for its task, has been a foundational primitive of access control for decades. We argue that this principle is insufficient for agentic AI systems, which do not merely hold permissions but can combine, approve, and amplify them across workflows and system boundaries. We propose least autonomy as an appropriate generalization and develop a formal theory. First, we define a compositional blast radius d(a,b) that measures structural separation between actions in an enterprise hierarchy, combining an ultrametric tree with lattice-valued confidentiality, integrity, and control-context labels. Second, we define a directed agent influence graph G(theta). An arc from U to V requires a directed shared-resource write-to-read meeting or a conservative undirected agent-to-agent (A2A) communication meeting, and a meeting-conditioned influence potential at or above an externally selected policy threshold theta. A catalogue-radius profile supports calibration and audit of theta. Finally, we define a collusion predicate over graph reachability that detects authorization composition, decision manipulation, and cross-domain capability composition.

Momentum

Related topics

Latest papers 311