LLM Agent Security

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

29 papers in the last four weeks, up 81% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 234

All topics

Swarm-Driven Multi-Agent Reasoning for Smart City Security
Jul 3, 2026Saeid Jamshidi, Kawser Wazed Nafi, Carol Fung +1Multi-Agent LLM Systems Cybersecurity
Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montr´eal, QC, Canada · SWAT Laboratory, Polytechnique Montréal, Montréal, QC, Canada
Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies
Jul 3, 2026Chris Schneider, Kriti Faujdar, Philipp Schoenegger +1LLM Agent Security Information Flow Control
1Microsoft AI · 2Microsoft
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
Steerability via constraints: a substrate for scalable oversight of coding agents
Jul 2, 2026Thomas WinningerScalable Oversight Coding Agents
Télécom SudParis, Évry-Courcouronnes, France · ENS Paris-Saclay, Gif-sur-Yvette, France
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
From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes
Jun 27, 2026Ting LiuMCP Security LLM Agent Security
SymbolicLight Research Foshan, Guangdong, China
When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration
Jun 27, 2026Luís Brito, Carlos BaqueroLLM Agent Security Multi-LLM Collaboration
Escola Superior de Tecnologia e Gestão (ESTG), Politécnico de Viana do Castelo (IPVC), Portugal · Faculdade de Engenharia (FEUP), Universidade do Porto (UP), Portugal
Capability Gates Are Not Authorization: Confused-Deputy Failures in LLM Agent Frameworks
Jun 27, 2026David Mellafe ZuvicAI Agent Auditing LLM Auditing
Independent Security Research Chile
Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare
Jun 27, 2026Liam KearnsMedical Report Generation RAG Poisoning Attacks
AuraQ Malvern Worcestershire UK
LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity
Jun 26, 2026Yiwei Xu, Yong Zhuang, Xuanming Liu +6Autonomous Cyber Defense LLM Agent Security
School of Cyber Science and Engineering, Wuhan University, Wuhan, China. · Department of Computer Science and Engineering, University at Buffalo, Buffalo, USA.
Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
Jun 25, 2026Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa +1Multi-Agent LLM Systems Multi-Agent Coordination
Oxford University · Artificial Intelligence Security Institute (AISI)
A Deterministic Control Plane for LLM Coding Agents
Jun 25, 2026Padmaraj MadathaAI Coding Agents LLM Guardrails
HappiestJuneMinds2026 Technologies (AIP Centre of Excellence)
Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
Jun 25, 2026Praneeth Narisetty, Shiva Nagendra Babu Kore, Uday Kumar Reddy Kattamanchi +1LLM Agent Evaluation LLM Agent Security
LaunchSafe Research
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
Detecting Malicious Agent Skills in the Wild using Attention
Jun 22, 2026Bacem Etteib, Daniele Lunghi, Tégawendé F. BissyandéLLM Agent Security Agent Skill Security Auditing
University of Luxembourg
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Jun 22, 2026Ruixiao Lin, Xinhao Deng, Qingming Li +12LLM Agent Security Self-Evolving Agents
1Zhejiang University · 2Ant Group · 3Tsinghua University +3
Black-Box Forensics for Conversational LLM Agents
Jun 21, 2026Isadora White, Yasaman Jafari, Taylor Berg-KirkpatrickLanguage Model Fingerprinting LLM Agent Security
University of California, San Diego
Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents
Jun 20, 2026Wangxuan Fan, Xiaoyu Nie, Zhongxiang DaiPrivacy-Preserving Language Models LLM Agent Security
The Chinese University of Hong Kong, Shenzhen
Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
Jun 19, 2026Zesen Liu, Zihan Zhang, Dongdong SheAdversarial Attacks on LLMs LLM Agent Security
The Hong Kong University of Science and Technology
Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer
Jun 19, 2026Zhengsong Zhang, Zongze Li, Jiawei Guo +1AI Agent Auditing Software Vulnerability Detection
Department of Computer Science and Engineering University at Buffalo, SUNY
When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
Jun 18, 2026Kaiyue Yang, Yuyan Bu, Jingwei Yi +5LLM Agent Security AI Agent Security Benchmarks
Institute of Information Engineering, Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence · The Chinese University of Hong Kong +2
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
Jun 16, 2026Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5LLM Safety Benchmarks LLM Agent Security
Peking University · Beijing Jiaotong University · SUIBE +2
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Jun 16, 2026Xiaojun Jia, Jie Liao, Simeng Qin +5LLM Agent Security Prompt Injection Defense
Nanyang Technological University, Singapore · Chongqing University, China · Northeastern University, China +2
The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs
Jun 15, 2026Sipeng Xie, Qianhong Wu, Hengrun Lu +4Remote Attestation LLM Agent Security
1Beihang University · 2Renmin University of China · 3Independent
SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills
Jun 14, 2026Ismail Hossain, Sai Puppala, Md Jahangir Alam +2LLM-as-a-Judge LLM Agent Security
SUPREME Lab, University of Texas at El Paso, Texas, USA.
TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI
Jun 14, 2026Qi Li, Zhenhua Zou, Shuo Li +2LLM Agent Security LLM Agent Routing
Tsinghua University
FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion
Jun 14, 2026Zixin Rao, Wentian Zhu, Chan Aristella Lu +5Adversarial Attacks on LLMs LLM Agent Security
University of Georgia · University of Chicago · University of Illinois Urbana-Champaign
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
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
Jun 13, 2026Yi Xie, Jiawei Du, Yu Cheng +2LLM Agent Security AI Agent Security Benchmarks
East China Normal University, Shanghai, China · Centre for Frontier AI Research A*STAR, Singapore · Shanghai Innovation Institute, Shanghai, China
Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization
Jun 13, 2026Kyle Gao, Pranavi Kotta, Linlin Xu +2Adversarial Robustness LLM Red Teaming
Department of Systems Design Engineering, University of Waterloo, Waterloo, ON, Canada · Department of Mechatronics Engineering, University of Waterloo, Waterloo, ON, Canada · Department of Geomatics Engineering, University of Calgary, Calgary, AB, Canada +1

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

Swarm-Driven Multi-Agent Reasoning for Smart City Security

Saeid Jamshidi, Kawser Wazed Nafi, Carol Fung, Foutse Khomh

Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montr´eal, QC, Canada · SWAT Laboratory, Polytechnique Montréal, Montréal, QC, Canada

Multi-Agent LLM Systems Cybersecurity LLM Agent Security Multi-Agent Reasoning LLM Agent Reliability

Open paper AskPDF arXiv

Modern smart cities are interconnected cyber-physical ecosystems where heterogeneous devices exchange data and control commands. Coordinated attacks may appear as weak and distributed indicators, including low-rate scanning, abnormal credential use, protocol misuse, or delayed lateral movement, with each signal remaining below local alert thresholds. Therefore, smart-city security is not only an anomaly detection task but also a reasoning task under uncertainty, partial observability, and adversarial manipulation. This work presents TPSC-Sec, an LLM-based multi-agent approach for stable security reasoning in smart cities. TPSC-Sec decomposes analysis across specialized agents that inspect traffic behavior, protocol interactions, identity usage, and temporal attack progression. Their independent threat hypotheses are aggregated by the proposed Threat-Pheromone Swarm Consensus mechanism, which reinforces supported hypotheses, suppresses contradictions, and preserves temporal consistency, thereby driving competing interpretations toward a stable collective decision. We further introduce Adaptive Verified TPSC, which adds verification-aware calibration, context-sensitive weighting, and disagreement-adaptive control to reduce unsupported LLM outputs and reasoning inconsistency. Experiments over 500 runs show that TPSC-Sec achieves a high consensus acceptance rate of 0.97 plus or minus 0.02, hypothesis-support concentration above 0.99, a consensus margin of 2.08 plus or minus 0.21, low aggregate risk of 0.23 plus or minus 0.04, high inter-agent agreement of 0.82 plus or minus 0.06, and strong support-quality correlation of r equals 0.93. Adaptive agent selection reduces the number of active agents by 50 percent while improving system fitness by 11.6 percent. These results demonstrate robust, interpretable, and efficient security reasoning for adversary-resilient smart-city environments.

Momentum

Related topics

Latest papers 234