AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents

• URL: http://arxiv.org/abs/2605.11026v1
• Date: Sun, 10 May 2026 20:08:27 GMT
• Title: AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents
• Abstract summary: AgentShield is a deception-based detection framework.<n>It places three layers of traps inside the agent's tool interface.<n>It catches 90.7%-100% of such successful attacks, with zero false alarms on 485 normal-use tests.
• Score: 4.36595961990666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such as Kurdish and Arabic without tested protection. This paper addresses both gaps with AgentShield, a deception-based detection framework that places three layers of traps inside the agent's tool interface: fake tools, fake credentials, and allowlisted parameters. The same trap triggers serve as high-precision labels for a self-supervised classifier. An LLM agent that follows an attacker's hidden instruction almost always touches one of these traps, which gives both a real-time compromise signal and a zero-FP label for training a downstream detector without manual annotation. Across 176 cross-lingual attack prompts and four LLMs from three providers, and because modern LLMs already refuse most IPI attempts on their own (attack success rate <= 10%), AgentShield's job is to catch the attacks that do slip through. On commercial models, it catches 90.7%-100% of such successful attacks, with zero false alarms on 485 normal-use tests. It survives a systematic adaptive-attack evaluation with zero evasion on commercial models, and the self-supervised classifier transfers across models and languages without retraining.

Related papers

• ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense [4.38737676286324]
  We present ZERO-APT, a turn-based attacker-defender-judge framework.<n>For realism, ZERO-APT embeds a LLM Defender that consumes Sysmon telemetry and detects attacks in real time.<n>For consistency, three architectural mechanisms move causal consistency from unstable LLM reasoning into enforced system architecture.
  arXiv  Detail & Related papers  (2026-06-04T01:28:36Z)
• Conjunctive Prompt Attacks in Multi-Agent LLM Systems [16.735743806437487]
  Inter-agent routing creates attack surfaces that single-agent evaluations miss.<n>We study emphconjunctive prompt attacks, where a trigger key in the user query and a hidden adversarial template in one compromised remote agent each appear benign alone but activate harmful behavior when routing brings them together.
  arXiv  Detail & Related papers  (2026-04-17T02:31:09Z)
• AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations [38.49666480491258]
  LLM agents are highly vulnerable to Indirect Prompt Injection (IPI)<n>We propose a new paradigm, action-level causal attribution, which secures agents by asking why a particular tool call is produced.<n>We instantiate this paradigm with AttriGuard, a runtime defense based on parallel counterfactual tests.
  arXiv  Detail & Related papers  (2026-03-11T13:23:46Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning [89.1856483797116]
  We introduce BEAT, the first framework to inject visual backdoors into MLLM-based embodied agents.<n>Unlike textual triggers, object triggers exhibit wide variation across viewpoints and lighting, making them difficult to implant reliably.<n>BEAT achieves attack success rates up to 80%, while maintaining strong benign task performance.
  arXiv  Detail & Related papers  (2025-10-31T16:50:49Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)
• Defeating Prompt Injections by Design [79.00910871948787]
  CaMeL is a robust defense that creates a protective system layer around the Large Language Models.<n>To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query.<n>To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows.
  arXiv  Detail & Related papers  (2025-03-24T15:54:10Z)
• Fine-tuned Large Language Models (LLMs): Improved Prompt Injection Attacks Detection [6.269725911814401]
  Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. This project explores the security vulnerabilities in relation to prompt injection attacks.
  arXiv  Detail & Related papers  (2024-10-28T00:36:21Z)
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents [84.96249955105777]
  LLM agents may pose a greater risk if misused, but their robustness remains underexplored.<n>We propose a new benchmark called AgentHarm to facilitate research on LLM agent misuse.<n>We find leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking.
  arXiv  Detail & Related papers  (2024-10-11T17:39:22Z)

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.