Cover Image

Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Pai, Aaditya
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
by: Xin, Yuan, et al.
Published: (2025)

Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems
by: Hackett, William, et al.
Published: (2025)

Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models
by: Del Rosario, Ron F.
Published: (2025)

Efficient LLM Safety Evaluation through Multi-Agent Debate
by: Lin, Dachuan, et al.
Published: (2025)

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
by: Miculicich, Lesly, et al.
Published: (2025)

Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents
by: Patlan, Atharv Singh, et al.
Published: (2025)

Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously
by: Adiletta, Andrew, et al.
Published: (2025)

JavelinGuard: Low-Cost Transformer Architectures for LLM Security
by: Datta, Yash, et al.
Published: (2025)

Detecting Prompt Injection Attacks Against Application Using Classifiers
by: Shaheer, Safwan, et al.
Published: (2025)

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
by: Nakamura, Mason, et al.
Published: (2025)

Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks
by: Shaheer, Safwan, et al.
Published: (2025)

Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design
by: Charles, Richard M., et al.
Published: (2025)

Large Language Models are Advanced Anonymizers
by: Staab, Robin, et al.
Published: (2024)

Adversarial Attacks on Large Language Models Using Regularized Relaxation
by: Chacko, Samuel Jacob, et al.
Published: (2024)

sudoLLM: On Multi-role Alignment of Language Models
by: Saha, Soumadeep, et al.
Published: (2025)

Quantifying Return on Security Controls in LLM Systems
by: Moulton, Richard Helder, et al.
Published: (2025)

Evaluating the efficacy of LLM Safety Solutions : The Palit Benchmark Dataset
by: Palit, Sayon, et al.
Published: (2025)

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults
by: Usman, Rana Muhammad
Published: (2026)

How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks
by: Wang, Yanshu, et al.
Published: (2026)

CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
by: Zhu, Yuxuan, et al.
Published: (2025)

Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
by: Kurian, Ashley, et al.
Published: (2025)

ConfusionPrompt: Practical Private Inference for Online Large Language Models
by: Mai, Peihua, et al.
Published: (2023)

Split-and-Denoise: Protect large language model inference with local differential privacy
by: Mai, Peihua, et al.
Published: (2023)

AI Safeguards, Generative AI and the Pandora Box: AI Safety Measures to Protect Businesses and Personal Reputation
by: Kumar, Prasanna
Published: (2026)

UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
by: Geng, Runpeng, et al.
Published: (2025)

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
by: Pulipaka, Sidharth, et al.
Published: (2026)

Send to which account? Evaluation of an LLM-based Scambaiting System
by: Siadati, Hossein, et al.
Published: (2025)

Defending against Backdoor Attacks via Module Switching
by: Li, Weijun, et al.
Published: (2025)

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
by: Cotti, Luca, et al.
Published: (2025)

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
by: Zhang, Tian, et al.
Published: (2026)

Scaling Trends in Language Model Robustness
by: Howe, Nikolaus, et al.
Published: (2024)

Exploiting Novel GPT-4 APIs
by: Pelrine, Kellin, et al.
Published: (2023)

Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study
by: Pissarra, David, et al.
Published: (2024)

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
by: Lelle, Travis
Published: (2026)

Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
by: Xie, Xiaopeng, et al.
Published: (2024)

Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
by: Young, Richard J.
Published: (2025)

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
by: Zhang, Peiyan, et al.
Published: (2025)

Measuring Harmfulness of Computer-Using Agents
by: Tian, Aaron Xuxiang, et al.
Published: (2025)

MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization
by: Gu, Yongtong, et al.
Published: (2026)

Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)
by: Verma, Apurv, et al.
Published: (2024)