Cover Image

LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Jiyuan, Jiang, Kaixun, Hong, Lingyi, Li, Jinglun, Guo, Haijing, Yang, Dingkang, Chen, Zhaoyu, Zhang, Wenqiang
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
by: Wang, Jiafeng, et al.
Published: (2022)

Improving Adversarial Transferability with Neighbourhood Gradient Information
by: Guo, Haijing, et al.
Published: (2024)

Boosting Adversarial Transferability with Spatial Adversarial Alignment
by: Chen, Zhaoyu, et al.
Published: (2025)

Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
by: Fu, Jiyuan, et al.
Published: (2024)

Delving into Decision-based Black-box Attacks on Semantic Segmentation
by: Chen, Zhaoyu, et al.
Published: (2024)

LoopTrap: Termination Poisoning Attacks on LLM Agents
by: Xu, Huiyu, et al.
Published: (2026)

VideoPure: Diffusion-based Adversarial Purification for Video Recognition
by: Jiang, Kaixun, et al.
Published: (2025)

A Theory of Composable Lingos for Protocol Dialects
by: García, Víctor, et al.
Published: (2026)

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
by: Fu, Jiyuan, et al.
Published: (2024)

Protocol Dialects as Formal Patterns: A Composable Theory of Lingos -- Technical report
by: García, Víctor, et al.
Published: (2025)

Enabling Efficient Attack Investigation via Human-in-the-Loop Security Analysis
by: Tsegai, Saimon Amanuel, et al.
Published: (2022)

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
by: Jiang, Kaixun, et al.
Published: (2025)

LLMs in Cybersecurity: Friend or Foe in the Human Decision Loop?
by: Pekaric, Irdin, et al.
Published: (2025)

Detecting Avalanche Effect in Adversarial Settings: Spotting the Encryption Loops in Ransomware
by: Luo, Nanqing, et al.
Published: (2026)

ARINC 429 Cyber-vulnerabilities and Voltage Data in a Hardware-in-the-Loop Simulator
by: Trask, Connor, et al.
Published: (2024)

LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation
by: Li, Xingyu, et al.
Published: (2025)

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
by: Mao, Yanxu, et al.
Published: (2025)

Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
by: Miao, Ziqi, et al.
Published: (2025)

Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning
by: Jiang, Yu, et al.
Published: (2024)

Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities
by: Ma, Yujie, et al.
Published: (2026)

ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
by: He, Ningyuan, et al.
Published: (2026)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
by: Zhang, Xu, et al.
Published: (2025)

Organizational Learning in Industry 4.0: Applying Crossan's 4I Framework with Double Loop Learning
by: Akram, Nimra, et al.
Published: (2025)

FlyTrap: Physical Distance-Pulling Attack Towards Camera-based Autonomous Target Tracking Systems
by: Xie, Shaoyuan, et al.
Published: (2025)

Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders
by: Jiang, Laura, et al.
Published: (2026)

The Harder You Try, The Harder You Fail: The KeyTrap Denial-of-Service Algorithmic Complexity Attacks on DNSSEC
by: Heftrig, Elias, et al.
Published: (2024)

Extracting Protocol Format as State Machine via Controlled Static Loop Analysis
by: Shi, Qingkai, et al.
Published: (2023)

The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction
by: Wang, He, et al.
Published: (2026)

Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection
by: Zhou, Yuqi, et al.
Published: (2024)

Privacy-Preserving Federated Unlearning with Certified Client Removal
by: Liu, Ziyao, et al.
Published: (2024)

Overthinking Loops in Agents: A Structural Risk via MCP Tools
by: Lee, Yohan, et al.
Published: (2026)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
by: Guo, Ji, et al.
Published: (2024)

Skip to Secure: Securing Cyber-physical Control Loops with Intentionally Skipped Executions
by: Adhikary, Sunandan, et al.
Published: (2020)

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
by: Wang, Wenqiang, et al.
Published: (2025)

MPMA: Preference Manipulation Attack Against Model Context Protocol
by: Wang, Zihan, et al.
Published: (2025)

SmartGraphical: A Human-in-the-Loop Framework for Detecting Smart Contract Logical Vulnerabilities via Pattern-Driven Static Analysis and Visual Abstraction
by: Fattahdizaji, Ali, et al.
Published: (2026)

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
by: Guo, Pinxue, et al.
Published: (2025)

SleepWalk: Exploiting Context Switching and Residual Power for Physical Side-Channel Attacks
by: Sanjaya, Sahan, et al.
Published: (2025)

Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers
by: Abad, Gorka, et al.
Published: (2024)

Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems
by: He, Jun, et al.
Published: (2026)