Image de couverture de livre

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Boxuan, Li, Zhuoyun, Huang, Xiaowei, Dong, Yi
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks
par: Wang, Boxuan, et autres
Publié: (2025)

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
par: Wang, Boxuan, et autres
Publié: (2025)

Position: Towards a Responsible LLM-empowered Multi-Agent Systems
par: Hu, Jinwei, et autres
Publié: (2025)

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
par: Li, Zhuoyun, et autres
Publié: (2026)

Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
par: Li, Zhuoyun, et autres
Publié: (2026)

Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
par: Zhang, Boxuan, et autres
Publié: (2025)

Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing
par: Hu, Jinwei, et autres
Publié: (2025)

Conjunctive Prompt Attacks in Multi-Agent LLM Systems
par: Arif, Nokimul Hasan, et autres
Publié: (2026)

Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
par: He, Qisong, et autres
Publié: (2026)

Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
par: Crawford, Brian, et autres
Publié: (2026)

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
par: Sehwag, Udari Madhushani, et autres
Publié: (2026)

PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
par: Huang, Xinmiao, et autres
Publié: (2026)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
par: Wang, Zhilong, et autres
Publié: (2025)

Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt
par: Huang, Zhenzhen, et autres
Publié: (2026)

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
par: Li, Yanjie, et autres
Publié: (2025)

Optimizing Service Operations via LLM-Powered Multi-Agent Simulation
par: Wang, Yanyuan, et autres
Publié: (2026)

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
par: Zhang, Kaiyuan, et autres
Publié: (2025)

DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
par: Hu, Jinwei, et autres
Publié: (2026)

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
par: Hu, Jinwei, et autres
Publié: (2026)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
par: Ning, Liang-bo, et autres
Publié: (2025)

Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
par: He, Shan, et autres
Publié: (2026)

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
par: Liu, Zesen, et autres
Publié: (2025)

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment
par: Hu, Jinwei, et autres
Publié: (2025)

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems
par: Balashov, Andrii, et autres
Publié: (2025)

Dreaming Is Not a Bug: A Jung-Inspired Dream Layer for Multi-Agent LLM Companions
par: Cheung, V.
Publié: (2026)

BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
par: Miao, Rui, et autres
Publié: (2025)

$\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks
par: Khan, Rana Muhammad Shahroz, et autres
Publié: (2025)

AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
par: Jiang, Tanqiu, et autres
Publié: (2026)

Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
par: Hao, Guangfu, et autres
Publié: (2026)

On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
par: Huang, Muhua, et autres
Publié: (2025)

Insider Attacks in Multi-Agent LLM Consensus Systems
par: Sun, Xiaolin, et autres
Publié: (2026)

SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning
par: Liang, Yanchang, et autres
Publié: (2026)

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
par: Lee, Donghyun, et autres
Publié: (2024)

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
par: Wang, Liwen, et autres
Publié: (2025)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
par: Zhu, Pengyu, et autres
Publié: (2025)

AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
par: Li, Yang, et autres
Publié: (2025)

Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective
par: You, Wangjie, et autres
Publié: (2025)

Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings
par: Kteich, Hanane, et autres
Publié: (2024)

Optimization-based Prompt Injection Attack to LLM-as-a-Judge
par: Shi, Jiawen, et autres
Publié: (2024)

PCoKG: Personality-aware Commonsense Reasoning with Debate
par: Li, Weijie, et autres
Publié: (2026)