Imagen de Portada

Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM Crowdsourcing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yan, Yu, Sun, Sheng, Li, Mingfeng, Song, Yunlong, Zhang, Xingzhou, Lu, Linran, Zheng, Zhifei, Liu, Min, Li, Qi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
por: Yan, Yu, et al.
Publicado: (2026)

BotSim: LLM-Powered Malicious Social Botnet Simulation
por: Qiao, Boyu, et al.
Publicado: (2024)

Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts
por: Ouyang, Sheng, et al.
Publicado: (2025)

Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars
por: Yan, Yu, et al.
Publicado: (2024)

Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
por: Zhang, Yunyi, et al.
Publicado: (2025)

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak
por: Wang, Hao, et al.
Publicado: (2024)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
por: Wang, Zhaoqi, et al.
Publicado: (2025)

MalTool: Malicious Tool Attacks on LLM Agents
por: Hu, Yuepeng, et al.
Publicado: (2026)

Assessing LLMs in Malicious Code Deobfuscation of Real-world Malware Campaigns
por: Patsakis, Constantinos, et al.
Publicado: (2024)

Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
por: Ji, Haoxuan, et al.
Publicado: (2024)

Just in Plain Sight: Unveiling CSAM Distribution Campaigns on the Clear Web
por: Lykousas, Nikolaos, et al.
Publicado: (2025)

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
por: Li, Xiangman, et al.
Publicado: (2025)

Unveiling the Visual Counting Bottleneck in Vision-Language Models
por: Pang, Xingzhou, et al.
Publicado: (2026)

Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information
por: Zhan, Xiao, et al.
Publicado: (2025)

MEEA: Mere Exposure Effect-Driven Confrontational Optimization for LLM Jailbreaking
por: Zhang, Jianyi, et al.
Publicado: (2025)

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
por: Yan, Yu, et al.
Publicado: (2025)

Distributed Information-theoretical Secure Protocols for Quantum Key Distribution Networks against Malicious Nodes
por: Luo, Yi, et al.
Publicado: (2023)

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
por: Li, Xirui, et al.
Publicado: (2024)

Bridging Expert Reasoning and LLM Detection: A Knowledge-Driven Framework for Malicious Packages
por: Guo, Wenbo, et al.
Publicado: (2026)

Speeding Ticket: Unveiling the Energy and Emission Burden of AI-Accelerated Distributed and Decentralized Power Dispatch Models
por: Li, Meiyi, et al.
Publicado: (2024)

SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking
por: Li, Jindong, et al.
Publicado: (2026)

DeepDiveAI: Identifying AI Related Documents in Large Scale Literature Data
por: Xiaochen, Zhou, et al.
Publicado: (2024)

xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
por: Lee, Sunbowen, et al.
Publicado: (2025)

DDRM: Distributed Drone Reputation Management for Trust and Reliability in Crowdsourced Drone Services
por: Akram, Junaid, et al.
Publicado: (2024)

Privacy-First Crowdsourcing: Blockchain and Local Differential Privacy in Crowdsourced Drone Services
por: Akram, Junaid, et al.
Publicado: (2024)

Highly Charged Triblock Bottlebrush Copolymers: Controlled Self‐Assembly Into Adaptive Porous Microspheres for Dynamic DNA Data Storage
por: Qiu‐Jun Liu, et al.
Publicado: (2025)

Redefining Research Crowdsourcing: Incorporating Human Feedback with LLM-Powered Digital Twins
por: Chan, Amanda, et al.
Publicado: (2025)

"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
por: Mei, Lingrui, et al.
Publicado: (2024)

Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspective
por: Tshimula, Jean Marie, et al.
Publicado: (2024)

Numerical Method‐Based Grain Temperature Distribution of Semi‐Underground Double‐Storey Squat Silos During Static Storage
por: Libing Jin, et al.
Publicado: (2025)

Crowdsourcing Task Traces for Service Robotics
por: Porfirio, David, et al.
Publicado: (2024)

Characterizing Event-themed Malicious Web Campaigns: A Case Study on War-themed Websites
por: Mia, Maraz, et al.
Publicado: (2025)

Getting Crowdsourcing Right: Aligning Crowdsourcing Goals and Decision‐Making Processes
por: Min Shuai, et al.
Publicado: (2025)

A Comparative Study on Annotation Quality of Crowdsourcing and LLM via Label Aggregation
por: Li, Jiyi
Publicado: (2024)

Unveiling Crowdfunding Futures: Analyzing Campaign Outcomes through Distributed Models and Big Data Perspectives
por: Pipitò, Giuseppe, et al.
Publicado: (2024)

A Distributed Malicious Agent Detection Scheme for Resilient Power Apportioning in Microgrids
por: Khatana, Vivek, et al.
Publicado: (2024)

Resilient Distribution Network Planning against Dynamic Malicious Power Injection Attacks
por: Sasahara, Hampei, et al.
Publicado: (2025)

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
por: Mo, Kanghua, et al.
Publicado: (2025)

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks
por: Liu, Sheng, et al.
Publicado: (2025)

Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
por: Chen, Honghao, et al.
Publicado: (2025)