ACIArena: Toward Unified Evaluation for Agent Cascading Injection

• URL: http://arxiv.org/abs/2604.07775v1
• Date: Thu, 09 Apr 2026 04:03:13 GMT
• Title: ACIArena: Toward Unified Evaluation for Agent Cascading Injection
• Abstract summary: ACIArena is a framework for evaluating the robustness of Multi-Agent Systems.<n>It offers evaluation suites spanning multiple attack surfaces and attack objectives.<n>It covers six widely used MAS implementations and provides a benchmark of 1,356 test cases.
• Score: 47.48169234218755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Collaboration and information sharing empower Multi-Agent Systems (MAS) but also introduce a critical security risk known as Agent Cascading Injection (ACI). In such attacks, a compromised agent exploits inter-agent trust to propagate malicious instructions, causing cascading failures across the system. However, existing studies consider only limited attack strategies and simplified MAS settings, limiting their generalizability and comprehensive evaluation. To bridge this gap, we introduce ACIArena, a unified framework for evaluating the robustness of MAS. ACIArena offers systematic evaluation suites spanning multiple attack surfaces (i.e., external inputs, agent profiles, inter-agent messages) and attack objectives (i.e., instruction hijacking, task disruption, information exfiltration). Specifically, ACIArena establishes a unified specification that jointly supports MAS construction and attack-defense modules. It covers six widely used MAS implementations and provides a benchmark of 1,356 test cases for systematically evaluating MAS robustness. Our benchmarking results show that evaluating MAS robustness solely through topology is insufficient; robust MAS require deliberate role design and controlled interaction patterns. Moreover, defenses developed in simplified environments often fail to transfer to real-world settings; narrowly scoped defenses may even introduce new vulnerabilities. ACIArena aims to provide a solid foundation for advancing deeper exploration of MAS design principles.

Related papers

• Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents [93.19140872946842]
  Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments.<n>This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour.<n>We introduce textbfsysname, a benchmark to systematically categorize and attribute harm in real-world web agent systems.
  arXiv  Detail & Related papers  (2026-06-11T14:12:43Z)
• AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses [1.247917923987062]
  Model Extraction Attacks (MEAs) enable adversaries to replicate proprietary models, compromise protected information, and prepare offline adversarial attacks.<n>Current defense strategies predominantly rely on the Single Client Assumption (SCA), which is the implicit assumption that attacks originate from isolated identities.<n>We introduce a modular, open-source framework called CerberusAI for reproducible model-stealing research, and use it to simulate distributed attack scenarios.
  arXiv  Detail & Related papers  (2026-06-02T09:25:29Z)
• OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage [59.3826294523924]
  We investigate the security vulnerabilities of a popular multi-agent pattern known as the orchestrator setup.<n>We report the susceptibility of frontier models to different categories of attacks, finding that both reasoning and non-reasoning models are vulnerable.
  arXiv  Detail & Related papers  (2026-02-13T21:32:32Z)
• Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening [23.066685616914807]
  We argue that effective agent security should be intrinsic and selective rather than architecturally decoupled and mandatory.<n>We propose Spider-Sense framework, which allows agents to maintain latent vigilance and trigger defenses only upon risk perception.<n>Spider-Sense achieves competitive or superior defense performance, attaining the lowest Attack Success Rate (ASR) and False Positive Rate (FPR)
  arXiv  Detail & Related papers  (2026-02-05T07:11:05Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• Cognitive Control Architecture (CCA): A Lifecycle Supervision Framework for Robustly Aligned AI Agents [1.014002853673217]
  LLM agents are vulnerable to Indirect Prompt Injection (IPI) attacks.<n>IPI attacks hijack agent behavior by polluting external information sources.<n>We propose the Cognitive Control Architecture (CCA), a holistic framework achieving full-lifecycle cognitive supervision.
  arXiv  Detail & Related papers  (2025-12-07T08:11:19Z)
• Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks? [58.48689960350828]
  We show that a simple, modular and model-agnostic defense operating at the agent--tool interface achieves perfect security with high utility.<n>We employ a defense based on two firewalls: a Tool-Input Firewall (Minimizer) and a Tool-Output Firewall (Sanitizer)
  arXiv  Detail & Related papers  (2025-10-06T18:09:02Z)
• Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms [1.03121181235382]
  Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains.<n>This study bridges this gap through comparative evaluation of Function Calling architecture and Model Context Protocol (MCP) deployment paradigms.<n>We tested 3,250 attack scenarios across seven language models, evaluating simple, composed, and chained attacks targeting both AI-specific threats and software vulnerabilities.
  arXiv  Detail & Related papers  (2025-07-08T18:24:28Z)
• ATAG: AI-Agent Application Threat Assessment with Attack Graphs [23.757154032523093]
  This paper introduces AI-agent application Threat assessment with Attack Graphs (ATAG)<n>ATAG is a novel framework designed to systematically analyze the security risks associated with AI-agent applications.<n>It facilitates proactive identification and mitigation of AI-agent threats in multi-agent applications.
  arXiv  Detail & Related papers  (2025-06-03T13:25:40Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents [60.30753230776882]
  LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect the agent to take unauthorized actions.<n>We present MELON, a novel IPI defense that detects attacks by re-executing the agent's trajectory with a masked user prompt modified through a masking function.
  arXiv  Detail & Related papers  (2025-02-07T18:57:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.