Copertina

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Zhaorun, Xiang, Zhen, Xiao, Chaowei, Song, Dawn, Li, Bo
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Cryptography and Security Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
di: Zhang, Baolei, et al.
Pubblicazione: (2025)

Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios
di: Rong, Dazhong, et al.
Pubblicazione: (2022)

Practical Poisoning Attacks against Retrieval-Augmented Generation
di: Zhang, Baolei, et al.
Pubblicazione: (2025)

Poisoning Federated Recommender Systems with Fake Users
di: Yin, Ming, et al.
Pubblicazione: (2024)

Traceback of Poisoning Attacks to Retrieval-Augmented Generation
di: Zhang, Baolei, et al.
Pubblicazione: (2025)

Unveiling Vulnerabilities of Contrastive Recommender Systems to Poisoning Attacks
di: Wang, Zongwei, et al.
Pubblicazione: (2023)

Secure Retrieval-Augmented Generation against Poisoning Attacks
di: Cheng, Zirui, et al.
Pubblicazione: (2025)

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
di: Zhang, Baolei, et al.
Pubblicazione: (2025)

Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures
di: Nguyen, Thanh Toan, et al.
Pubblicazione: (2024)

Poisoning Decentralized Collaborative Recommender System and Its Countermeasures
di: Zheng, Ruiqi, et al.
Pubblicazione: (2024)

Poisoning Attacks and Defenses in Recommender Systems: A Survey
di: Wang, Zongwei, et al.
Pubblicazione: (2024)

Preserving Privacy and Utility in LLM-Based Product Recommendations
di: Khezresmaeilzadeh, Tina, et al.
Pubblicazione: (2025)

RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
di: Jia, Austin, et al.
Pubblicazione: (2025)

MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion
di: Lin, Zilong, et al.
Pubblicazione: (2023)

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
di: Chen, Zhaorun, et al.
Pubblicazione: (2025)

Retrieval-Augmented Review Generation for Poisoning Recommender Systems
di: Yang, Shiyi, et al.
Pubblicazione: (2025)

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

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

DM4Steal: Diffusion Model For Link Stealing Attack On Graph Neural Networks
di: Chen, Jinyin, et al.
Pubblicazione: (2024)

Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
di: Wang, Chunxiao
Pubblicazione: (2026)

Randomized algorithms for precise measurement of differentially-private, personalized recommendations
di: Laro, Allegra, et al.
Pubblicazione: (2023)

Multi-Faceted Studies on Data Poisoning can Advance LLM Development
di: He, Pengfei, et al.
Pubblicazione: (2025)

Watermarking Recommender Systems
di: Zhang, Sixiao, et al.
Pubblicazione: (2024)

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
di: Yang, Shiyi, et al.
Pubblicazione: (2025)

Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation
di: Liu, Yinuo, et al.
Pubblicazione: (2025)

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning
di: Guo, Junfeng, et al.
Pubblicazione: (2025)

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
di: Yao, Mengyu, et al.
Pubblicazione: (2026)

Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approach
di: Hu, Wentao, et al.
Pubblicazione: (2023)

A Privacy Preserving System for Movie Recommendations Using Federated Learning
di: Neumann, David, et al.
Pubblicazione: (2023)

Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
di: Liu, Yu-An, et al.
Pubblicazione: (2024)

LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
di: Lim, Juntaek, et al.
Pubblicazione: (2024)

Adversarial Attacks to Multi-Modal Models
di: Dou, Zhihao, et al.
Pubblicazione: (2024)

How to Forget Clients in Federated Online Learning to Rank?
di: Wang, Shuyi, et al.
Pubblicazione: (2024)

Auditing Privacy in Multi-Tenant RAG under Account Collusion
di: Burnat, Florian A. D.
Pubblicazione: (2026)

Safe machine learning model release from Trusted Research Environments: The SACRO-ML package
di: Smith, Jim, et al.
Pubblicazione: (2022)

HGAttack: Transferable Heterogeneous Graph Adversarial Attack
di: Zhao, He, et al.
Pubblicazione: (2024)

Few-shot Model Extraction Attacks against Sequential Recommender Systems
di: Zhang, Hui, et al.
Pubblicazione: (2024)

Effective and secure federated online learning to rank
di: Wang, Shuyi
Pubblicazione: (2024)

Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion
di: Thornton, Scott
Pubblicazione: (2026)

Differentially Private Graph Diffusion with Applications in Personalized PageRanks
di: Wei, Rongzhe, et al.
Pubblicazione: (2024)