Cover Image

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aichberger, Lukas, Paren, Alasdair, Li, Guohao, Torr, Philip, Gal, Yarin, Bibi, Adel
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ToolTweak: An Attack on Tool Selection in LLM-based Agents
by: Sneh, Jonathan, et al.
Published: (2025)

Shh, don't say that! Domain Certification in LLMs
by: Emde, Cornelius, et al.
Published: (2025)

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
by: Zhang, Jiawei, et al.
Published: (2025)

Vera Verto: Multimodal Hijacking Attack
by: Zhang, Minxing, et al.
Published: (2024)

Multi-Agent Systems Execute Arbitrary Malicious Code
by: Triedman, Harold, et al.
Published: (2025)

MAIDS: Malicious Agent Identification-based Data Security Model for Cloud Environments
by: Gupta, Kishu, et al.
Published: (2024)

CHAI: Command Hijacking against embodied AI
by: Burbano, Luis, et al.
Published: (2025)

VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
by: Du, Xuefeng, et al.
Published: (2024)

RobPI: Robust Private Inference against Malicious Client
by: Xue, Jiaqi, et al.
Published: (2026)

Model Hijacking Attack in Federated Learning
by: Li, Zheng, et al.
Published: (2024)

Detecting Malicious AI Agents Through Simulated Interactions
by: Pi, Yulu, et al.
Published: (2025)

Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems
by: Jha, Rishi, et al.
Published: (2025)

Malicious Internet Entity Detection Using Local Graph Inference
by: Mandlik, Simon, et al.
Published: (2024)

Osmosis Distillation: Model Hijacking with the Fewest Samples
by: Shi, Yuchen, et al.
Published: (2026)

Beyond Crash: Hijacking Your Autonomous Vehicle for Fun and Profit
by: Sun, Qi, et al.
Published: (2026)

Design Patterns for Securing LLM Agents against Prompt Injections
by: Beurer-Kellner, Luca, et al.
Published: (2025)

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
by: Davies, Xander, et al.
Published: (2025)

FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems
by: Long, Yuzhen, et al.
Published: (2025)

OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage
by: Naik, Akshat, et al.
Published: (2026)

Image Hijacks: Adversarial Images can Control Generative Models at Runtime
by: Bailey, Luke, et al.
Published: (2023)

Moshi Moshi? A Model Selection Hijacking Adversarial Attack
by: Petrucci, Riccardo, et al.
Published: (2025)

GasTrace: Detecting Sandwich Attack Malicious Accounts in Ethereum
by: Liu, Zekai, et al.
Published: (2024)

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models
by: Liang, Jiacheng, et al.
Published: (2025)

ML Study of MaliciousTransactions in Ethereum
by: Katz, Natan
Published: (2024)

Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection
by: Kimura, Subaru, et al.
Published: (2024)

AIJack: Let's Hijack AI! Security and Privacy Risk Simulator for Machine Learning
by: Takahashi, Hideaki
Published: (2023)

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
by: Chen, Zhaorun, et al.
Published: (2025)

Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage Classification
by: Li, Yujie, et al.
Published: (2024)

Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias
by: Bernstein, Shir, et al.
Published: (2025)

Your Agent Can Defend Itself against Backdoor Attacks
by: Changjiang, Li, et al.
Published: (2025)

Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents
by: Lukáš, Ondřej, et al.
Published: (2026)

Toward More Generalized Malicious URL Detection Models
by: Tsai, YunDa, et al.
Published: (2022)

A New Dataset and Methodology for Malicious URL Classification
by: Schvartzman, Ilan, et al.
Published: (2024)

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
by: Suri, Anshuman, et al.
Published: (2025)

Towards Quantum Machine Learning for Malicious Code Analysis
by: Lopez, Jesus, et al.
Published: (2025)

SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection
by: Erdogan, Ege, et al.
Published: (2023)

Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems
by: Peng, Qizhou, et al.
Published: (2025)

Hijack Vertical Federated Learning Models As One Party
by: Qiu, Pengyu, et al.
Published: (2022)

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
by: Foerster, Hanna, et al.
Published: (2025)

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
by: Jin, Weifei, et al.
Published: (2026)