Multi-Agent System Security

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 200% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 112

Aug 4, 2026cs.AI

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners. Existing agent benchmarks study tool use and collaboration, but they do not provide an end-to-end sandbox for verifiable cross-user agent collaboration with realistic user digital workspaces or test how harmful actions can travel through the human-centered agent network. We introduce WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. WeClawArena targets collaborative tool-use tasks in which personal workspaces serve as both operational tools and personal constraints. The benchmark contains 124 base tasks across six cross-user task domains and expands them into 620 scenario variants, with one benign control and four attack-vector variants per base task. The sandbox records peer messages, tool calls, resource operations, governed decisions, and final workspace states. WeClawArena reports utility and attack success rate separately and audits attack success from bounded runtime evidence, supporting diagnosis of task breakdown, privacy leakage, poisoned evidence, and invalid authority paths.

Prince Zizhuang Wang, Aojie Yuan, Haiyue Zhang +3

Carnegie Mellon University · University of Southern California · Arizona State University

Multi-Agent Collaboration AI Agent Security Benchmarks Tool-Using Agents Multi-Agent System Security

Aug 4, 2026cs.IR

Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity

Multi-agent collaborative filtering (CF) systems coordinate autonomous LLM-powered user and item agents through natural-language interaction to refine preferences and generate recommendations. These systems inherit vulnerabilities from both their data-driven nature and their multi-agent interactions, which manifest in distinct ways. Understanding how connectivity modulates vulnerability in these systems could facilitate the development of more robust recommendation pipelines. In this work, we adapt attacks and defenses from the general multi-agent systems (MAS) literature to the agent-based CF setting, evaluating them under systematically varied connectivity in the AgentCF framework, where CF connectivity is characterized along two axes: (i) candidate count (the number of item candidates per turn per user, measuring user-side interaction density) and (ii) catalog concentration (the degree of item catalog overlap across users). Our contributions include: (1) Adaptation: we reproduce MAS-inspired attacks and defenses in the agentic CF domain, confirming partial transferability of original observations. (2) Characterization: we characterize how the two aspects of connectivity shape attack and defense outcomes, revealing role asymmetries between user and item agents, non-monotonic temporal dynamics in attack efficacy, and divergent patterns across dissemination and extraction attack goals. Additionally, as an exploratory extension, we assess the applicability of epidemic-inspired static metrics in ranking CF configurations by expected attack outcome, potentially enabling cost-efficient robustness assessment. Implementation is available at https://github.com/anjunhu/ConnACF

Anjun Hu, Hanting Xie, Saranya Govindan +2

University of Oxford · Amazon

Multi-Agent Systems Recommender Systems Multi-Agent System Security Collaborative Filtering

Aug 3, 2026cs.CR

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach

Tool-using agents built on large language models (LLMs) are increasingly deployed not by a single operator but by many, side by side on shared infrastructure. This creates a population-level risk that single-agent safeguards miss: a handful of agents can quietly coordinate, rigging a market, boosting one another in a review process, or timing a joint data grab, while each one looks perfectly well-behaved. The difficulty is that the organisations running these agents cannot see inside one another's models, so any realistic detector must work from behaviour alone: black-box, trace-only, and often with only partial visibility. We treat covert coordination as an information-hiding problem and build a black-box steganalysis detector that combines cross-run mutual-information estimation, permutation tests, distributional-shift statistics, and timing and tool-call side channels, all calibrated to a fixed false-positive budget. Our central move is to stop testing against a single fixed code: we pit the detector against an adversary that continually rewrites its encoding to slip past whatever the detector has learned, and we run this red-versus-blue contest in tool-using, memory-carrying environments rather than toy games. Capacity theory then tells us what to expect, a detection-capacity frontier, a covert bit-rate below which black-box detection is provably no better than chance. We set out an experiment to map this frontier, report clearly labelled placeholder results pending measurement, and flag a practical evasion, spreading a payload across sessions, that current methods largely miss.

Mohamed Chahine Ghanem

Keele University, Newcastle-Under-Lyme, U.K.

Algorithmic Collusion AI Agent Monitoring Multi-Agent System Security

Aug 3, 2026cs.AI

Securing Agentic AI: From Per-Action Checks to Trajectory Assurance

Autonomous agents are increasingly used to execute consequential tasks in environments governed by operational constraints, organizational policies, regulatory requirements, and technical standards. Their safety is therefore determined not by the correctness of individual actions, but by whether their overall behavior remains consistent with the rules and invariants of the systems in which they operate. As large language model (LLM)-based agents become more autonomous and increasingly delegate tasks across organizational boundaries, securing them evolves from a single challenge into a broad and interconnected landscape spanning the entire agentic stack. At the single-agent level, untrusted inputs through prompts, memory, retrieved knowledge, and tool interfaces create attack surfaces. In multi-agent settings, delegation and communication introduce challenges related to identity, trust, capability control, and decision transparency, while the underlying model routing and execution control plane remains vulnerable to manipulation and to unverified model provenance. Perhaps the most fundamental challenge is behavioral containment: sequences of individually permissible actions may collectively violate system-level constraints and safety invariants. At the broader level, supply-chain integrity, provenance, accountability, and end-to-end observability remain largely open problems. A common principle unifies these directions: security must become a verifiable property of the architectures, protocols, and runtimes that govern agent behavior, rather than an optional layer of guidance. Charting these challenges provides a roadmap toward trustworthy autonomous agent deployment.

Alireza Lotfi, Subangkar Karmaker Shanto, Imtiaz Karim +1

Purdue University · Department of Computer Science · West Lafayette, IN, USA +2

AI Agent Security LLM Agent Security AI Agent Safety Tool Access Control for LLM Agents Multi-Agent System Security

Aug 2, 2026cs.MA

When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems

LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduces a vulnerability: backdoor behavior can be activated when peer evidence reaches a hidden threshold, rather than being determined by any single message. We introduce a collective evidence-threshold backdoor paradigm for MAS and Boundary-Conditioned Backdoor Injection (BCBI), which constructs counterfactual boundary pairs to separate benign behavior before the threshold from the adversarial objective after it, and learns latent progression aligned with evidence. To mitigate this threat, we propose LAtent Transition Test-time Evaluation (LATTE), a clean-only latent-transition defense that learns benign communication dynamics and quarantines anomalous agent updates before their responses propagate. Across several benchmarks, BCBI yields selective activation with little premature activation; without knowing the attack target or trigger, LATTE limits propagation with minimal disruption.

Jia-Hao Xiao, Lei Feng, Min-Ling Zhang

School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · Key Laboratory of Computer Network and Information Integration (Southeast University)

Multi-Agent LLM Systems Backdoor Attacks Multi-Agent System Security

Aug 2, 2026cs.MA

MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures

Multi-agent systems (MAS) decompose long-horizon tasks across supervisors and subagents, but delegated goals do not necessarily carry their original authorization boundaries. Existing safety benchmarks mainly study adversarial compromise, while work on constraint drift lacks controlled architecture-level evaluation. We introduce MasDrift, a benchmark of 600 benign productivity tasks across eight domains. Each task pairs required work with reserved actions. MasDrift compares single-agent, centralized, and decentralized coordination while varying hierarchy depth and peer width, measuring task completion and authorization preservation. Across generic multi-agent conditions, centralized hierarchies achieve 93.9--98.6% task completion versus 85.7--87.0% for peer networks, while unauthorized actions occur in 2.7--19.8% of tasks versus 0.6--0.8%, a gap that widens with hierarchy depth. We further compare two defenses that differ in where authorization evidence resides. One re-anchors every pending call to the original user request. The other carries an attenuated policy along the delegation chain. Re-anchoring reduces unauthorized actions in every model configuration we evaluate, at a cost of 1.6 points of pooled completion. Chain propagation blocks required work instead, forfeiting up to 36.3 points. A heterogeneous case study confirms that the failure follows from coordination rather than model strength. MasDrift exposes a centralization tradeoff and makes authorization preservation a measurable property of MAS design.

Zhuoning Xu, Xiucheng Zhang, Hanjun Luo +3

New York University · New York University Abu Dhabi · The Hong Kong Polytechnic University +1

Multi-Agent Coordination Multi-Agent Orchestration AI Agent Safety Benchmarks Multi-Agent System Security

Aug 1, 2026cs.MA

MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems

LLM-based multi-agent systems (MAS) increasingly rely on persistent private and shared memories for long-horizon coordination. This memory layer improves continuity, but it also gives attackers a durable channel: a poisoned memory can be written once, continuously retrieved in later tasks, promoted into shared memory, and reused by other agents. A single poisoned write can therefore steer many later decisions and contaminate agents that never saw the original attack, all while no malicious message crosses a visible communication edge at the moment of harm. Further, because existing safeguards mainly inspect prompts, actions, or communication edges, they can miss attacks whose content appears benign at write time but becomes harmful after retrieval. We introduce Memory-Aware Propagation and Link Enforcement Guard, MAPLE-Guard, a memory-link guard for memory-enabled MAS. MAPLE-Guard monitors the memory lifecycle and places gates at write, retrieval, promotion, and cross-agent reuse, so risky memories can be quarantined, unsafe retrievals filtered, and poisoned private memories blocked before they enter shared memory. In the main evaluation, MAPLE-Guard lowers attack success rate (ASR) from 38.2% to 0.9% on LongMemEval and from 34.7% to 0.2% on AppWorld; it also raises multi-agent defense success rate (MDSR) from 54.0% to 74.3% and from 42.5% to 99.8% on the same benchmarks. These results suggest that memory-aware link enforcement covers a gap left by prompt-level and topology-level defenses. Code is available at the link: https://github.com/xiong-wenjun/MAPLE-Guard.

Wenjun Xiong, Yijin Zhou, Jiaqian Wang +6

Shanghai Jiao Tong University · Shanghai Innovation Institute · Xidian University +2

Multi-Agent LLM Systems Agent Memory Poisoning Multi-Agent System Security Agent Memory Management Shared-Memory Multi-Agent Systems

Jul 31, 2026cs.CR

Skillsets on the Chain: A Blockchain-based Zero-Trust Framework for Agentic AI Networking

Agentic AI networking (AgentNet) systems rely heavily on third-party skillset implementations and distributed multi-agent collaboration, yet they face major claim-to-capability inconsistencies and security vulnerabilities under trust-by-declaration assumptions. To bridge this gap, this paper proposes TrustAgentNet, a dual-tier blockchain-secured zero-trust framework. Specifically, a global Chain of Skillsets (CoS) governs the lifecycle of skillset metadata with protocols empowered by specialized agents to enforce off-chain auditing while maintaining lightweight on-chain cryptographic consensus. Furthermore, transient, task-oriented Chains of Collaboration (CoC) are dynamically established to enable trustless distributed multi-agent collaboration. Theoretical analysis of the three-way trade-off among security level, task performance, and resource overhead is provided and empirically validated. Experimental results on a hardware prototype demonstrate that compared with no-blockchain trust-by-default baselines, the zero-trust overhead of TrustAgentNet is dominated by off-chain inference, while the blockchain layer incurs minor ledger costs via the ledger-IPFS storage and on/off-chain integration design. Crucially, the proposed verification pipeline achieves a flawless 100% accuracy across 50 AI models, correctly validating 40 honest skillsets and intercepting 10 adversarial ones, and generalizes to non-AI domains with an 83.91% accuracy and a 0.85 F1-score across 1478 features from 171 ClawHub skills. Adversarial experiments further show that TrustAgentNet enables autonomous skillset self-recovery against various malicious attacks.

Yayu Gao, Yong Xiao, Hao Hu +5

School of Electronic Information and Communications, the Huazhong University of Science and Technology, Wuhan, China 430074 · Peng Cheng Laboratory, Shenzhen, China · Pazhou Laboratory (Huangpu), Guangzhou, China +4

Cybersecurity AI Agent Security Agent Skill Security Auditing Multi-Agent System Security Zero-Trust Security Agentic AI

Jul 28, 2026cs.MA

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective can be fragmented into locally plausible subtasks, allowing malicious intent to evade detection by any single agent. This is a growing social-impact challenge: systems handling sensitive information or consequential tools can turn routine delegation into unauthorized disclosure or unsafe action. We argue that this failure mode is better understood as a semantic information-flow problem than as a single-turn prompt classification task. To address this, we propose SafeFlow, a defense framework for multi-agent systems that formalizes malicious cross-agent propagation as a semantic information-flow problem. SafeFlow attaches structured semantic taints to root requests, propagates them through a dynamic collaboration graph, and performs workflow-level validation to reconstruct the global risk context before irreversible actions are committed. Evaluated on four benchmarks spanning prompt injection, jailbreak-based unsafe tool use, risky code execution, and harmful web-agent behavior, SafeFlow reduces attack success rates compared to undefended baselines and external defenses while retaining high benign task completion and a high paired safe--harm success rate. Our findings show that multi-agent systems still lack mechanisms for preserving risk semantics across delegation boundaries. This gap can turn routine delegation into privacy harms or unsafe actions that affect people and organizations. SafeFlow keeps this risk visible throughout the workflow, before it results in harm.

Haowen Dai, Zonghao Ying, Wenfeng Li +10

University of Nottingham Ningbo China · Beihang University · Shandong University +6

AI Agent Safety Information Flow Control Prompt Injection Attacks on AI Agents Multi-Agent System Security

Jul 27, 2026cs.CR

Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study

Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run. Per-step safety checks that judge each action in isolation may fail to recognize the complete distributed payload. We investigate how early such an attack can be detected while the run is still unfolding, and how robustly it can be caught once its most obvious cues are stripped away. We build a working instance on a hierarchical multi-agent system, run it under benign and attacked conditions across five language models and two task domains, and record when each fragment is injected and when the payload is assembled and executed. Detection is a race against assembly. Before the first fragment is injected, attacked and benign runs are indistinguishable; once injection begins, a prefix detector flags

99.3\%

of successful attacks with a median of five steps remaining and a

10.3\%

safe-run false-positive rate. Because assembly occurs only after the run, these alarms arrive in time to abort nearly every successful attack. We then measure how much of that warning rests on removable surface cues of the attack rather than on its distributed structure. Generic zero-shot and behavior-trained detectors provide almost no warning at all; the detectors that do work lean in part on removable surface cues, chiefly the ciphertext's length and entropy, and once the entropy cue is removed from the payload and the length features from the detector, detection arrives later and transfers poorly across domains, though a fine-tuned model recovers some of the loss.

Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang +1

Illinois Institute of Technology Chicago, Illinois, USA

Multi-Agent LLM Systems LLM Backdoor Attacks Backdoor Attacks Backdoor Detection AI Agent Monitoring Multi-Agent System Security

Jul 26, 2026cs.CR

Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric

Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested environments. A growing class of their assurance failures arises not within any single platform but across the swarm: individually-compliant actions compose into a mission-level violation: a prohibited objective split across platforms to evade per-platform lim- its, or a collective budget quietly exceeded. Per-platform guardrails miss these by construction, and contested communications let the violation hide behind lost or delayed evidence. We present a three-tier (platfor- m/squad/mission) compositional runtime-verification framework that de- composes a mission policy into per-agent and cross-agent aspects, aggre- gates per-platform verdicts over a verification-aware messaging fabric, and fuses them with an evidence-aware, two-axis (security x complete- ness) algebra whose provenance names the platforms that jointly trig- gered a violation. Because the fabric makes evidence loss and silence observable, unsupported negative verdicts are downgraded to an explicit unknown rather than reported as mission-wide all-clears. On a simulated ISR mission, an indirect prompt injection that causes real LLM planners to split a prohibited collection task across four platforms is invisible to every per-platform monitor yet detected compositionally with full prove- nance; under an injected fault campaign a best-effort central monitor emits silent false all-clears while the verification-aware fabric emits none

Nikolaos Kekatos, Panagiotis Katsaros, Alexios Lekidis +2

Clone Systems, Larnaca, Cyprus · Aristotle University of Thessaloniki, Thessaloniki, Greece · University of Thessaly, Larissa, Greece

Swarm Robotics AI Agent Monitoring LLM Agent Safety Multi-Agent System Security Runtime Verification

Jul 14, 2026cs.AI

Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only about input--output content alignment. It also concerns system behavior and real-world execution outcomes. However, the current literature is fragmented across attack types, applications, and benchmarks. This makes it hard to explain why failures such as prompt injection, tool misuse, and memory poisoning often share the same structural cause, and how they spread through an agent workflow. In this survey, we treat isolation as a first-class principle for LLM-agent system safety. By isolation, we refer to the separation of user inputs, tool access, execution channels, inter-agent communication, and environment-originated context. We organize the literature with a boundary-centric taxonomy of five boundaries: user-agent, agent-tool, agent-execution, agent-agent, and system-environment. This view helps identify where the loss of isolation first occurs, how compromise propagates across boundaries, and which defenses are most relevant at each interface. We also summarize cross-boundary failure paths, discuss open challenges, and outline a research agenda for isolation-by-construction in future agent systems.

Huihao Jing, Wenbin Hu, Shaojin Chen +10

HKUST · NYU · SWUPL

LLM Agent Security LLM Agent Safety Tool Access Control for LLM Agents Multi-Agent System Security

Jul 13, 2026cs.CR

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems

As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembled object is the attack. The monitor can be right on every step and still miss the attack. The problem is not splitting itself: split fragments can still leak suspicious tokens or provenance edges. The hard case is \emph{local benignness}. No fragment carries the harm, and what is left looks like ordinary benign traffic. We formalize this as an \emph{observability boundary}: a monitor catches only what its view can tell apart from benign traffic. We prove that once the fragments look benign in the monitored view, no detector on that view can catch them, however strong it is. Across a controlled testbed, an external benchmark, and end-to-end agent runs, local monitors lose the signal exactly as local evidence disappears, and it returns only when the monitor sees the assembled object. A monitor trained only on benign traffic recovers the attack's code structure across held-out encodings (0.874 mean AUROC). A decoded-view gate, given the encoding family, blocks every tested attack. But seeing more is not enough: full-trace monitors and decoders still fail unless they reach the representation where the payload is exposed. Local safety is not global safety when harm is compositional, and the open problem is finding that representation.

Yibo Hu, Ren Wang

Illinois Institute of Technology

Backdoor Attacks Backdoor Detection AI Agent Monitoring Multi-Agent System Security

Jul 10, 2026cs.CR

VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents

Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. While recent adoptions of Large Language Model (LLM) agents have demonstrated promise in penetration testing and Capture-the-Flag (CTF) environments, their application to IoT specific vulnerabilities remains unexplored. This paper presents an autonomous multi-agent framework, referred to as Vulnerability EXploitation using AI Agents (VEXAIoT), for vulnerability discovery and exploitation in IoT environments using LLM-based reasoning and offensive security tools. The framework combines a vulnerability detection agent and an attack execution agent to perform reconnaissance, plan attack sequences, and execute exploits against vulnerable IoT services. The system is evaluated in IoTGoat and Metasploitable environments across ten attack scenarios mapped to OWASP IoT vulnerabilities. Experimental results show attack success rate of up to 100% with low token overhead and average execution times under two minutes for most attacks. Across 260 attack executions, VEXAIoT achieves a 95.0% overall success rate, including 94.5% success in IoTGoat and 96.7% success in Metasploitable2. These results demonstrate the potential for LLM-driven agents to automate IoT vulnerability assessment and offensive security workflows in controlled environments

Katherine Swinea, Kshitiz Aryal, Lopamudra Praharaj +1

Department of Computer Science, Tennessee Tech University, TN, USA. · School of Interdisciplinary Informatics, University of Nebraska Omaha, NE, USA. · Dept. of Mathematics & Computer Science, University of North Carolina at Pembroke, NC, USA.

Cybersecurity LLM Agent Security Automated Penetration Testing Multi-Agent System Security

Jul 7, 2026cs.CR

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels. Most existing MAS security defenses are built upon two core assumptions: semantically-explicit malicious attacks and explicit graph-based modeling of the MAS topology and agent-level interactions. In practice, real-world attacks are becoming more semantically stealthy, while MAS execution is typically asynchronous without the temporal alignment assumed by graph-based propagation models. To address these limitations, we propose AcMAS, an activation-based framework for malicious-behavior detection in MAS. By analyzing internal reasoning states in the activation space of local agents, AcMAS detects even stealthy attacks in a synchronization-robust fashion, without relying on explicit interaction graphs. Moreover, our activation analysis provides critical signals to guide AcMAS in restoring the functionality of compromised agents, rather than the disruptive agent isolation commonly used by the state-of-the-art methods. Comprehensive evaluation demonstrates that AcMAS significantly outperforms graph-based baselines against stealthy attacks, by +0.22 F1 in synchronous settings (0.94 vs. 0.72) and by +0.55 F1 in asynchronous settings (0.93 vs. 0.38), with generalization across diverse open-source LLM backbones, attack intensity, and MAS scale.

Haowen Xu, Xue Tan, Lei Ma +6

Department of Computer Science, Worcester Polytechnic Institute, MA, USA · School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China +1

LLM Agent Security AI Agent Monitoring Multi-Agent System Security Anomaly Detection

Jul 7, 2026cs.RO

CILC: Cryptographically-secure Inter-agent Loop Closure Candidate Detection for Multi-Agent Collaborative SLAM

Multi-agent Simultaneous Localization and Mapping (SLAM) and collaborative SLAM (CSLAM) require robots to continuously exchange global descriptors (GDs) to detect inter-agent loop closures (ILCs). While encrypted radios protect this traffic from external eavesdroppers, they offer no protection against a compromised swarm member. We show this threat is concrete by demonstrating how a corrupted agent can reconstruct approximations of an honest agent's imagery and trajectory from its public GD broadcasts. To address this, we propose CILC (Cryptographically-secure Inter-agent Loop Closure candidate detection), a first-of-its-kind system leveraging Secure Multi-Party Computation (SMPC) to detect ILC candidates without exchanging GDs in the clear. Rather than securing the entire CSLAM pipeline, we apply SMPC only to ILC candidate detection (i.e., GD similarity comparison), a privacy-sensitive yet computationally lightweight step, yielding an advantageous privacy-to-overhead trade-off. We validate in both simulation and hardware experiments that CILC remains real-time and communication-feasible across multimodal GDs (visual and LiDAR), while mitigating information leakage to a compromised swarm agent.

Andrew Fishberg, Yixuan Jia, Jonathan P. How

Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.

Simultaneous Localization and Mapping Secure Multi-Party Computation Multi-Robot Systems Multi-Agent System Security

Jul 6, 2026cs.RO

Governed Caste Reassignment in Heterogeneous Swarms: An Asymmetric-Trust Protocol with Audited Operator Countersignature

In heterogeneous robot swarms, caste reassignment (rebinding a robot to a new capability-bound role) is a high-frequency runtime event driven by battery, payload, and priority changes. Existing approaches treat it as an internal allocation algorithm and do not expose the reassignment to external authority. We argue that for regulated embodied deployments a caste change that elevates a robot's privilege envelope is a governance event that must be auditable and externally authorised. We propose an asymmetric-trust protocol: auto-tightening reassignments (to safer, lower-privilege castes) are admitted automatically, while bounded relaxation (to higher-privilege castes) requires an operator countersignature against a per-axis budget. Each transition carries a signed cause-chain, committed to a hash-chained Merkle audit log that an offline auditor verifies from an operator-signed identity manifest alone. We evaluate a reference implementation with real Ed25519 signatures over fleets up to 100 robots: auto-tightening completes in single-digit to low-double-digit milliseconds, and the governed protocol refuses four explicit attacks (caste laundering, repeated-relaxation escalation, operator impersonation, cause-chain forgery) by construction, with a partially-governed baseline isolating which gate stops which attack and a randomized fuzz adversary finding no admission. A distributed audit layer replicates the log across N per-member replicas with quorum-committed total order and cryptographic fork exclusion; we prove agreement and fork exclusion and validate them both in simulation and as a real multi-process deployment over TCP sockets (up to 100 real processes) with a Byzantine equivocator, on which every honest replica agrees, detects the equivocation, and commits no fork. The construction generalises a single-agent persona-mutation governance gate to swarm-level caste governance.

Xue Qin, Simin Luan, Cong Yang +1

School of Software, Harbin Institute of Technology, Harbin, China. · School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China. · School of Future Science and Engineering, Soochow University, Suzhou, China.

Algorithmic Auditing Swarm Robotics AI Agent Governance Multi-Agent System Security

Jul 5, 2026cs.RO

LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems

Uncrewed Aerial Vehicle (UAV) swarms have significant potential for applications such as Search and Rescue (SAR) and environmental monitoring, but their real-world deployment is limited by a lack of situational awareness, intermittent connectivity, and significant cybersecurity risks. Agentic Artificial Intelligence (AI) represents a shift from standalone Large Language Model (LLM) toward closed-loop cognitive architectures that integrate perception, memory, reasoning/planning, and action to enable adaptive, goal-directed swarm behavior. Within this framework, Agentic AI provides a unifying structure for autonomous and adaptive swarm operations while expanding the system attack surface compared to conventional AI systems. This paper proposes LLM-Centric Agentic AI for UAV Swarms (LAUS) and reviews key enabling technologies such as onboard and edge computing, 5G/6G connectivity, multimodal intelligence, and cybersecurity mechanisms, and analyzes threats such as Priority Manipulation Attacks (PMA) that can distort decision-making and degrade network performance. Finally, it identifies open research challenges, including hallucination-resistant reasoning, onboard LLM deployment under SWaP constraints, and standardized security benchmarks for perception-reasoning attacks in agentic UAV systems.

Yousef Emami, Rahim Taheri, Mohammadhossein Homaei +2

Senior Member, IEEE

Multi-Agent LLM Systems AI Agent Security Multi-Robot Coordination Multi-Agent System Security Agentic AI

Jul 3, 2026cs.AI

A Theory of Least Autonomy in AI

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.

Christophe Parisel

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

Jun 29, 2026cs.CR

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend against. In this paper, we address how defenders should prioritize limited security effort to protect vulnerable communication channels before attacks are observed. This is motivated by our observation that the channel-level attack impact is highly non-uniform: a single compromised edge can account for up to 75% of total attack success. We introduce Mesa, a label-free framework for proactively ranking which MAS edges are most security-critical -- that is, most likely to affect the system's decision if compromised. Mesa combines six graph-theoretic metrics and two dynamic probes (ablation and masking) without requiring attack traces. We evaluate Mesa against a dynamic misinformation attack pipeline across three diverse MAS scenarios, eight network topologies, and five open-source LLMs from Qwen, Llama, and Gemma families. Mesa rankings correlate strongly with empirical per-edge attack success rate, achieving mean Spearman

ρ=+0.60

(peaking at

+0.73

). In resource-constrained defense deployment, monitoring the top 10% of Mesa-ranked edges intercepts about 3x the successful attacks as random allocation. We further test Mesa under varying attacker and defender models and LangGraph workflows and characterize its limits under adaptive attacks and high-redundancy graphs. Overall, our results show that edge-level risk in MAS is often concentrated and predictable, allowing proactive hardening of multi-agent infrastructures.

Kunyang Li, Kyle Domico, Jonathan Gregory +1

University of Wisconsin–Madison

AI Agent Monitoring Multi-Agent System Security Multi-Agent Communication

Jun 29, 2026cs.AI

Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing

The rapid integration of Large Language Models (LLMs) has driven the evolution of Multi-Agent Systems (MAS), where specialized agents collaborate to execute complex workflows. Effective orchestration in these environments requires robust routing mechanisms to efficiently allocate tasks to the most suitable agent. However, existing routers fundamentally rely on unverified proxies, ranging from textual self-descriptions to static surrogate representations, to gauge an agent's competence. This reliance on non-empirical data creates a critical gap between an agent's projected profile and its actual operational capabilities, introducing severe security vulnerabilities. Malicious agents can easily misrepresent their proficiencies or harbor covert backdoors that evade both standard external analysis and static representation-learning techniques. In this work, we introduce ANTAP (Automatic Non-Textual Agent Picker), an evaluation-driven routing architecture that discards indirect proxies in favor of active capability testing. By dynamically querying agents to ascertain their true competencies empirically, ANTAP distills performance into fixed behavioral operators within a shared semantic space. At inference time, routing is performed via a purely non-textual algebraic projection, establishing a "linguistic firewall" that renders metadata-based attacks inexpressible. In our experiments, ANTAP achieves near-zero ASR against description-based injection attacks, compared to 67.3% and above for the description-based router baseline. Against adaptive embedding attacks, ANTAP achieves substantially lower ASR than the embedding-based baseline, with a 20% reduction, while remaining resilient to description manipulation by design.

Dvir Alsheich, Adar Peleg, Ben Hagag +3

1Technion - Israel Institute of Technology · 2Carnegie Mellon University

Adversarial Attacks on LLMs Agent Evaluation Multi-Agent System Security LLM Agent Routing

Jun 26, 2026cs.AI

Agent-Native Immune System: Architecture, Taxonomy, and Engineering

The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has fundamentally expanded the AI threat landscape. Current defense mechanisms, such as perimeter security and training-time alignment, remain external to the agent's active reasoning loop. Consequently, they fall short: a fully aligned agent remains highly vulnerable to runtime hijacking via memory poisoning, tool-chain manipulation, or multi-agent protocol attacks. To address this critical gap, we introduce the Agent-Native Immune System (ANIS), the first biologically inspired, endogenous defense architecture embedded directly within the agent's cognitive loop. Our framework presents four primary contributions. First, we design a six-layer Immune Tower (L0-L5), distinctly incorporating Barrier Immunity (L1) as a non-cognitive, physical-and-logical isolation layer. Second, we establish a unified taxonomy of Agent Viruses and Agent Vaccines, formalizing the critical distinction between superficial non-parametric defenses and robust parametric vaccines. Third, we conceptualize the Harness Triad--Meta, Self, and Auto--a self-monitoring, meta-cognitive automation backbone that drives Continual Immune Learning (CIL), enabling vaccines to dynamically adapt to novel threats. Finally, we establish a rigorous theoretical demarcation between model alignment and agent immunity: while alignment provides a static "constitutional" value foundation during training, ANIS serves as the dynamic "law enforcement" mechanism during runtime. We conclude by framing open challenges for the field, including immune protocol standardization, novel evaluation metrics such as the Autoimmunity Rate (false-positive intervention rate), and the co-evolutionary dynamics between pathogens and vaccines within collective intelligence ecosystems.

Bo Shen, Lifeng Chang, Tianyuan Wei +7

Novo Ordo for AI

AI Agent Security AI Agent Monitoring Multi-Agent System Security

Jun 25, 2026eess.SY

Resilient Output Containment under Undisclosed Leader Dynamics and Actuator Attacks

This work studies resilient output containment for heterogeneous linear multi-agent systems with actuator cyber-attacks over directed network topologies. The leaders generate bounded locally absolutely continuous trajectories; however, their dynamics, velocity bounds, and motion envelopes are undisclosed to the followers. The cyber-attack model includes state- and input-correlated, as well as bounded exogenous actuator false-data terms. A continuous two-layer adaptive control architecture is proposed. The first layer is a virtual-actuator reconfiguration layer that uses partial state measurements to compensate for actuator attacks in the local tracking-error dynamics. The second layer is a network interface that generates task-space commands via an adaptive interaction protocol. This protocol uses only neighbor-exchanged network-interface states whose dimensions match those of the plant output, and it does not require global graph knowledge for parameter tuning. For directed graphs, under a leader-rooted united spanning-tree condition, a nonsmooth Lyapunov analysis yields asymptotic containment at the command level. The physical outputs then converge to the leader convex hull up to a residual determined by the command-tracking local controllers. Simulation results using a network of quadrotors with damped suspended loads illustrate the performance of attack recovery and containment tracking.

Mohammadreza Nematollahi, Khashayar Khorasani, Nader Meskin

Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada. · Department of Electrical Engineering, Qatar University, Doha, Qatar.

Cyber-Physical Systems Multi-Agent Control Robust Control Multi-Agent System Security Adaptive Control

Jun 23, 2026cs.AI

Governed Shared Memory for Multi-Agent LLM Systems

Multi-agent LLM environments require robust mechanisms for shared knowledge management. This paper formalizes the fleet-memory problem and identifies four foundational failure modes: unauthorized leakage, stale propagation, contradiction persistence, and provenance collapse. To address these, we define explicit systems-level primitives: scoped retrieval, temporal supersession, provenance tracking, and policy-governed memory propagation. These primitives are implemented in MemClaw, a production multi-tenant memory service, and evaluated via ArgusFleet, a reproducible harness testing four governance dimensions. Rather than a baseline comparison, this study measures a live production service, emphasizing real-world architectural insights and negative results. Key Evaluation Results Provenance: Successfully reconstructed 100% of depth-four derivation chains with correct writer identity at sub-second per-hop latency. Propagation: Demonstrated high intra-fleet visibility with zero cross-fleet leakage. Under strong write mode, write-to-visible latency was optimized to a single search round-trip. Production Architectural Issues Discovered Asymmetric Scope Enforcement: Tenant isolation held, but sub-tenant scope was initially bypassed on direct GET-by-id requests for agent-scoped credentials (disclosed and remediated during the study). Pipeline Ordering Conflict: While contradiction supersession works for admitted writes, a synchronous near-duplicate gate can prematurely reject contradictory writes before the asynchronous contradiction detector can evaluate them. Conclusion: Long-context retrieval alone is insufficient for production multi-agent memory. Governed shared memory demands explicit systems-level abstractions, and live evaluation is vital to expose enforcement and pipeline-ordering failures missed by design-only treatments.

Yanki Margalit, Nurit Cohen-Inger, Erni Avram +2

Computer Science and Information, Ben-Gurion University of the Negev

Multi-Agent LLM Systems Data Provenance LLM Agent Memory Multi-Agent System Security Agent Memory Management Shared-Memory Multi-Agent Systems

Jun 16, 2026cs.CR

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System (IRS) framework that converts alerts from IDS, EDR, and XDR platforms into structured incident response plans grounded in MITRE ATT&CK, MITRE D3FEND, and NIST CSF 2.0. Agentra decomposes response reasoning across role-scoped agents, validates proposed plans through a bounded Planner--Validator review loop, screens retrieved threat intelligence through a Moderator security gateway, gates actions through an Action Catalog and risk score, and records decisions in an append-only audit log. We evaluate Agentra against a static OASIS CACAO v2.0 cyber-playbook baseline on a 120-event corpus drawn from ThreatHunter-Playbook, Splunk BOTSv3, and DARPA OpTC. The strongest configuration improves FP-aware IRS F1 from 0.61 to 0.84 and restores the projected harmful-action rate to the static baseline level of 0.0% after Planner-only configurations introduce unsafe overreaction. These results indicate that multi-agent response planning can improve ontology-grounded IRS coverage while preserving analyst approval and auditability.

Raj Patel, Shaswata Mitra, Michele Guida +3

The University of Alabama, Alabama, USA · Roma Tre University, Rome, Italy

Autonomous Cyber Defense AI Agent Safety Multi-Agent System Security

Jun 15, 2026cs.MA

BARD-MARL: Byzantine-Agent Detection for Learned Communication in Multi-Agent Reinforcement Learning

Learned communication improves coordination in cooperative multi-agent reinforcement learning, but it also creates a trust problem: a trained policy may route information through agents that have become faulty or adversarial. This paper studies Byzantine-agent detection for learned-communication MARL in adaptive traffic signal control. We propose BARD-MARL, a post-hoc diagnostic layer on top of BayesG, which is used as an attributed communication substrate rather than as a contribution of this paper. BARD-MARL combines two agent-level evidence streams: policy-graph features extracted from state-action trajectories and Bayesian trust statistics computed from BayesG latent mask probabilities. Across fixed-action, observation-flip, random-noise, and coordinated attacks in SUMO traffic grids, the results show that these signals are complementary rather than universally dominant. On a 25-agent grid, BARD-MARL reaches 0.843 AUC-ROC under a 10% observation-flip attack, while policy-graph-only detection reaches 0.917 AUC-ROC under a 10% coordinated attack. On a 100-agent grid, the unified BARD-MARL variant reaches 0.982 AUC-ROC for both 10% fixed-action and 10% coordinated attacks. The study shows that learned communication policies expose useful diagnostic evidence, but credible resilience claims require attack-specific ablations and explicit separation between coordination, detection, and mitigation.

Almond Kiruthu Murimi

Carnegie Mellon University Department of Electrical and Computer Engineering Pittsburgh, Pennsylvania, United States

Multi-Agent Systems Multi-Agent System Security Multi-Agent Communication Cooperative MARL

Jun 13, 2026cs.CR

Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization

Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversational and spatial analysis but introduces security risks. This work presents a security-oriented framework for risk identification, evaluation, and mitigation in a multi-agent GIS system while maintaining adaptability to broader agentic architectures. We test the agentic system of a commercial geospatial partner while developing a modular state-machine-based orchestration framework that abstracts agent behavior into reusable components. We evaluate robustness using a red-teaming framework with an adaptive attacker LLM and a deterministic judge that produces binary outcomes with supporting rationales across multi-turn attacks. We further improve resilience with a prompt optimization framework that treats prompts as structured signatures and injects adversarial demonstrations, enabling systematic security improvements without degrading task performance.

Kyle Gao, Pranavi Kotta, Linlin Xu +2

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

Adversarial Robustness LLM Red Teaming LLM Agent Security Multi-Agent System Security

Jun 11, 2026cs.CR

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particularly under coordinated adversarial behaviors such as privilege escalation and cross-agent collusion. Existing red-teaming approaches for MAS remain limited: they rely on heuristic selection of target agents and perturb isolated message streams, leaving critical questions unanswered as which agents are most responsible for system safety, and how compromised agents can coordinate to bypass defenses. We propose MAStrike, a closed-loop framework for collusive red-teaming in hierarchical MAS. We propose the first agent-level Shapley value analysis for MAS, quantifying each agent's marginal contribution to system robustness under task-specific distributions. GGuided by this attribution, MAStrike identifies vulnerable agent coalitions and generates coordinated, role-aware adversarial manipulations. These attacks are iteratively refined through structured causal diagnosis, attributing failure cases to uncompromised agents that block adversarial attempts. We further build a comprehensive MAS red-teaming benchmark and controllable environments spanning diverse hierarchical topologies and domains, including finance, software engineering, and CRM. Extensive experiments across MAS built on multiple frontier models show that MAStrike substantially outperforms heuristic baselines. Our analysis further uncovers non-trivial Shapley value distributions and higher-order interaction structures among agents, revealing critical vulnerabilities and coordination patterns that are overlooked by prior single-agent or template-based methods.

Chejian Xu, Zhaorun Chen, Jingyang Zhang +5

University of Illinois, Urbana-Champaign · Virtue AI · University of Chicago +3

AI Agent Security Benchmarks Shapley Value Attribution Multi-Agent Systems Automated Red Teaming Multi-Agent System Security

Jun 10, 2026cs.MA

Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the interaction between model scaling and system-level resilience remains poorly understood. This paper investigates how model scale affects the security of linear multi-agent workflows. Our experiments across scales of two open-weight model families on the HumanEval benchmark reveal a compliance-correction symmetry: larger models are far more likely to faithfully execute malicious instructions, with the control-to-malicious performance drop reaching 53.7pp at 27B in uncorrected pipelines. However, appending a lightweight terminal Fixer stage collapses this to 0.6pp and restores statistical parity with control-level performance, demonstrating that strictly linear collaboration structures can be viable and resilient to adversaries at this scale, and suggesting that the brittleness previously attributed to linear topology may stem from a lack of correction.

Timothy McAllister, Sina Abdidizaji, Ivan Garibay +1

Department of Computer Science, University of Central Florida, Orlando, FL, USA · Department of Industrial Engineering, University of Central Florida, Orlando, FL, USA

AI Agent Security LLM Agent Security Prompt Injection Attacks on AI Agents Multi-Agent System Security Multi-Agent LLMs

Jun 10, 2026cs.MA

SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems

LLM-based multi-agent systems (MAS) solve complex tasks through inter-agent collaboration, but their communication-driven nature also allows security risks to spread across agents and trigger system-wide failures. Existing MAS defenses mainly follow a reactive paradigm after execution by detecting and isolating harmful agents, which may cause irreversible damage and degrade collaborative utility. To address this, we propose a proactive defense framework for MAS security, namely a Simulation-aware Interception Guard (SAIGuard). SAIGuard performs communication-state simulation over the MAS interaction graph, estimates the impact of incoming messages on local agent states and the global MAS state, and detects risky messages via reconstruction deviations from benign communication patterns. Instead of isolating agents, SAIGuard sanitizes or regenerates suspicious messages before it propagation into system. Experiments across diverse topologies and attack scenarios show that SAIGuard reduces attack success rates while maintaining MAS utility, outperforming reactive defenses.

Ruxue Shi, Yili Wang, Mengnan Du +4

School of Artificial Intelligence, Jilin University, Changchun, China · The Chinese University of Hong Kong, Shenzhen, China · School of Information and Communication Technology, Griffith University, Australia

LLM Agent Security Multi-Agent System Security Multi-Agent Communication Anomaly Detection