MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures

Zhuoning Xu; Xiucheng Zhang; Hanjun Luo; Yingbin Jin; Yinpeng Dong; Hanan Salam

cs.MAAug 2, 2026

MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures

Authors: Zhuoning Xu, Xiucheng Zhang, Hanjun Luo, Yingbin Jin, Yinpeng Dong, Hanan Salam

Abstract

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.

Explore similar work

Apr 25, 2026cs.MA

Architecture Matters for Multi-Agent Security

Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual agents exhibit robust security, architectural decisions governing their coordination can create attack surfaces that have not been systematically characterized. In this work, we present an empirical study of how MAS design decisions shape the tradeoff between task performance and attack resistance. Across three agentic environments (browser, desktop, and code) and 13 architectural configurations, we use stagewise evaluations that distinguish planning refusal, execution-stage interception, partial harmful execution, and successful attack completion to study three key design choices: (i) agent roles, which determine how authority and responsibility are allocated; (ii) communication topology, which shapes how and when agents interact; and (iii) memory, which determines the context and state visibility accessible to each agent. We find that multi-agent architectures are more vulnerable than standalone agents in the majority of configurations, with attack success rates varying by up to 3.8x at comparable or higher benign accuracy, and that no single design is universally safer. These results motivate the development of further evaluations that move beyond the security properties of a single agent.

Ben Hagag, William L. Anderson, Christian Schroeder de Witt +1

Multi-Agent Systems Security Single-Agent

Ask PDF

Sep 1, 2026cs.CR

SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems

Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-agent setting can easily be mistaken for evidence of a genuinely multi-agent security effect. We thus systematize MAS security through an execution-centered analysis of 197 works, covering six interaction interfaces, four adversary positions, seven system-level risks, and eight recurring attack paths. We introduce an A-I-R framework that organizes attacks by adversary position, interaction interface, and resulting system-level risk, unifying otherwise fragmented attack mechanisms across MAS. We organize defenses through a five-part contract covering path target, observation, intervention, trust boundary, and recovery, and identify path closure and recovery as key challenges. We audit 44 evaluation and benchmark works and identify open challenges in isolating interaction effects, designing comparable and diagnostic metrics, supporting reuse across MAS designs, and evaluating open-system operation. Together, these findings motivate an interaction-aware view of MAS security: trace attacks end to end, test whether defenses close those paths, and evaluate system-level effects with appropriate counterfactuals.

Rui Yang, Junjie Xu, Zhengyu Liu +4

Multi-Agent Systems Multi-Agent Large Language Model Systems Agentic Systems Security Transferable Attack

Ask PDF

May 6, 2026cs.AI

Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure

The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve data, delegate tasks, and synthesize results across changing boundaries. We call this problem authorization propagation. It is not reducible to prompt injection and is not fully addressed by classical access-control models such as RBAC, ABAC, or ReBAC. The paper formalizes authorization propagation as a workflow-level property, identifies three sub-problems (transitive delegation, aggregation inference, and temporal validity), and derives seven structural requirements for authorization architectures in multi-agent AI systems. Recent work on invocation-bound capability tokens, task-scoped authorization envelopes, dependency-graph policy enforcement, and execution-count revocation demonstrates that the field is converging on the problem, but not yet on a complete architecture. The central claim is that identity governance must be treated as infrastructure: evaluated continuously, enforced at every interaction boundary, and designed into the system before orchestration logic is allowed to scale. Preliminary implementation evidence from a production enterprise AI platform shows that ordinary system behavior, not only adversarial action, already produces the failures this model predicts.

Krti Tallam

Authorization Delegation Agentic Systems Multi-Agent Systems Dependency Graph

Ask PDF