Cover Image

OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Kaixiang, Lou, Jiong, Zhou, Zhaojiacheng, Li, Jie
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems
by: Zhou, Zhaojiacheng
Published: (2026)

MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS
by: Wang, Kaixiang, et al.
Published: (2025)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
by: Srivastava, Saksham Sahai, et al.
Published: (2025)

DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruning
by: Zhao, Kaixiang, et al.
Published: (2025)

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
by: Halloran, John T., et al.
Published: (2026)

SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization
by: Singampalli, Akhil, et al.
Published: (2024)

Have You Poisoned My Data? Defending Neural Networks against Data Poisoning
by: De Gaspari, Fabio, et al.
Published: (2024)

Scaling Trends for Data Poisoning in LLMs
by: Bowen, Dillon, et al.
Published: (2024)

FedReview: A Review Mechanism for Rejecting Poisoned Updates in Federated Learning
by: Zheng, Tianhang, et al.
Published: (2024)

The Autonomy Tax: Defense Training Breaks LLM Agents
by: Li, Shawn, et al.
Published: (2026)

Reasoning-Style Poisoning of LLM Agents via Stealthy Style Transfer: Process-Level Attacks and Runtime Monitoring in RSV Space
by: Zhou, Xingfu, et al.
Published: (2025)

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

KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation
by: Chen, Qizhi, et al.
Published: (2026)

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
by: Bhat, Sunay, et al.
Published: (2024)

Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
by: Carnerero-Cano, Javier, et al.
Published: (2026)

ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
by: Xu, Zhangchen, et al.
Published: (2024)

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
by: Duan, Kaiwen, et al.
Published: (2025)

Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection
by: Gabrielli, Edoardo, et al.
Published: (2023)

Enhancing Cloud Network Resilience via a Robust LLM-Empowered Multi-Agent Reinforcement Learning Framework
by: Peng, Yixiao, et al.
Published: (2026)

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
by: Lobo, Elita, et al.
Published: (2024)

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
by: Zhang, Heyi, et al.
Published: (2025)

Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts
by: Wu, Yuanwei, et al.
Published: (2023)

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
by: Zhao, Kaixiang, et al.
Published: (2026)

Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
by: Thornton, Scott
Published: (2026)

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
by: Xu, Yuancheng, et al.
Published: (2024)

A Survey on Model Extraction Attacks and Defenses for Large Language Models
by: Zhao, Kaixiang, et al.
Published: (2025)

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives
by: Zhao, Kaixiang, et al.
Published: (2025)

A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments
by: Zhao, Kaixiang, et al.
Published: (2025)

Policy-Invisible Violations in LLM-Based Agents
by: Wu, Jie, et al.
Published: (2026)

Reliable Weak-to-Strong Monitoring of LLM Agents
by: Kale, Neil, et al.
Published: (2025)

FHE-Agent: Automating CKKS Configuration for Practical Encrypted Inference via an LLM-Guided Agentic Framework
by: Xu, Nuo, et al.
Published: (2025)

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
by: Nie, Yuzhou, et al.
Published: (2024)

PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
by: Yan, Bingyu, et al.
Published: (2026)

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

FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in FL
by: Hallaji, Ehsan, et al.
Published: (2025)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
by: Xu, Yinglun, et al.
Published: (2024)

Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
by: Zhang, Yujie, et al.
Published: (2024)

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
by: Kutasov, Jonathan, et al.
Published: (2025)

BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning
by: Liu, Yi, et al.
Published: (2024)

EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learning
by: Meerza, Syed Irfan Ali, et al.
Published: (2024)