Cover Image

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Naen, An, Hengyu, Shi, Shuo, Zhang, Jinghuai, Zhou, Chunyi, Li, Changjiang, Du, Tianyu, Fu, Zhihui, Wang, Jun, Ji, Shouling
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ACIArena: Toward Unified Evaluation for Agent Cascading Injection
by: An, Hengyu, et al.
Published: (2026)

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
by: An, Hengyu, et al.
Published: (2025)

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
by: Xu, Naen, et al.
Published: (2025)

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
by: Xu, Naen, et al.
Published: (2026)

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
by: Xu, Naen, et al.
Published: (2025)

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
by: Yin, Rui, et al.
Published: (2026)

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
by: He, Ping, et al.
Published: (2025)

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
by: Chen, Jiahao, et al.
Published: (2026)

DP-GENG : Differentially Private Dataset Distillation Guided by DP-Generated Data
by: Shi, Shuo, et al.
Published: (2025)

Rethinking the Vulnerabilities of Face Recognition Systems:From a Practical Perspective
by: Chen, Jiahao, et al.
Published: (2024)

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing
by: Chen, Jiahao, et al.
Published: (2025)

Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
by: Li, Changjiang, et al.
Published: (2024)

Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models
by: Chu, Fengheng, et al.
Published: (2026)

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
by: Wang, Peiran, et al.
Published: (2026)

FreeTalk:A plug-and-play and black-box defense against speech synthesis attacks
by: Pu, Yuwen, et al.
Published: (2025)

Dullahan: Stealthy Backdoor Attack against Without-Label-Sharing Split Learning
by: Pu, Yuwen, et al.
Published: (2024)

Unveiling the Security Risks of Federated Learning in the Wild: From Research to Practice
by: Chen, Jiahao, et al.
Published: (2026)

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data
by: Pu, Yuwen, et al.
Published: (2024)

When Skills Lie: Hidden-Comment Injection in LLM Agents
by: Wang, Qianli, et al.
Published: (2026)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
by: Yang, Xianglin, et al.
Published: (2026)

The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability
by: Xu, Zijie, et al.
Published: (2025)

Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection
by: Wei, Yangyang, et al.
Published: (2026)

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
by: Ma, Oubo, et al.
Published: (2024)

CAMH: Advancing Model Hijacking Attack in Machine Learning
by: He, Xing, et al.
Published: (2024)

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
by: Zhang, Chuhan, et al.
Published: (2025)

Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
by: Ma, Oubo, et al.
Published: (2026)

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
by: Ma, Oubo, et al.
Published: (2025)

Enhancing Adversarial Transferability with Adversarial Weight Tuning
by: Chen, Jiahao, et al.
Published: (2024)

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
by: Chen, Xuan, et al.
Published: (2026)

On the Security Risks of ML-based Malware Detection Systems: A Survey
by: He, Ping, et al.
Published: (2025)

Imprompter: Tricking LLM Agents into Improper Tool Use
by: Fu, Xiaohan, et al.
Published: (2024)

MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning
by: Wang, Zhiqiang, et al.
Published: (2025)

From Alerts to Intelligence: A Novel LLM-Aided Framework for Host-based Intrusion Detection
by: Sun, Danyu, et al.
Published: (2025)

Prompt Injection Attack to Tool Selection in LLM Agents
by: Shi, Jiawen, et al.
Published: (2025)

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems
by: Wang, Xiaoqing, et al.
Published: (2025)

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
by: Liu, Shi, et al.
Published: (2026)

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
by: Li, Fanxiao, et al.
Published: (2026)

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
by: Zeng, Rui, et al.
Published: (2024)

Reframing LLM Agent Security as an Agent-Human Interaction Problem
by: Wang, Peiran, et al.
Published: (2026)

PentestAgent: Incorporating LLM Agents to Automated Penetration Testing
by: Shen, Xiangmin, et al.
Published: (2024)