Cover Image

Deep-Research Agents Can Be Poisoned via User-Generated Content

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Tingwei, Triedman, Harold, Shmatikov, Vitaly
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Agent Systems Execute Arbitrary Malicious Code
by: Triedman, Harold, et al.
Published: (2025)

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
by: Jha, Rishi, et al.
Published: (2026)

Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems
by: Jha, Rishi, et al.
Published: (2025)

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives
by: Zhang, Collin, et al.
Published: (2024)

How to Steal Reasoning Without Reasoning Traces
by: Zhang, Tingwei, et al.
Published: (2026)

Adversarial Illusions in Multi-Modal Embeddings
by: Zhang, Tingwei, et al.
Published: (2023)

Differential Degradation Vulnerabilities in Censorship Circumvention Systems
by: Sun, Zhen, et al.
Published: (2024)

Adversarial Hubness in Multi-Modal Retrieval
by: Zhang, Tingwei, et al.
Published: (2024)

Self-interpreting Adversarial Images
by: Zhang, Tingwei, et al.
Published: (2024)

Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents
by: Shafran, Avital, et al.
Published: (2024)

Universal Zero-shot Embedding Inversion
by: Zhang, Collin, et al.
Published: (2025)

Rerouting LLM Routers
by: Shafran, Avital, et al.
Published: (2025)

MillStone: How Open-Minded Are LLMs?
by: Triedman, Harold, et al.
Published: (2025)

Defending against Data Poisoning Attacks in Federated Learning via User Elimination
by: Galanis, Nick
Published: (2024)

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation
by: Ye, Hengkai, et al.
Published: (2026)

PoisonCatcher: Revealing and Identifying LDP Poisoning Attacks in IIoT
by: Shuai, Lisha, et al.
Published: (2024)

Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning
by: Deng, Gelei, et al.
Published: (2024)

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
by: Chen, Zhaorun, et al.
Published: (2024)

Electric Democracy: Proof of Work to secure Elections
by: Zuevsky, Vitaly
Published: (2022)

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
by: Guo, Ruoqi, et al.
Published: (2026)

Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing
by: Sun, Desen, et al.
Published: (2026)

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

PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
by: Panaitescu-Liess, Michael-Andrei, et al.
Published: (2025)

MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
by: Chen, Tailun, et al.
Published: (2025)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
by: Zou, Wei, et al.
Published: (2026)

LoopTrap: Termination Poisoning Attacks on LLM Agents
by: Xu, Huiyu, et al.
Published: (2026)

BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
by: Tie, Guiyao, et al.
Published: (2026)

CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
by: Li, Chunyang, et al.
Published: (2025)

Blockchain Address Poisoning
by: Tsuchiya, Taro, et al.
Published: (2025)

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

Data Poisoning in Deep Learning: A Survey
by: Zhao, Pinlong, et al.
Published: (2025)

Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
by: Xie, Yueqi, et al.
Published: (2024)

Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?
by: Sasnauskas, Paulius, et al.
Published: (2025)

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
by: Zhang, Guangsheng, et al.
Published: (2026)

Data Poisoning for In-context Learning
by: He, Pengfei, et al.
Published: (2024)

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

Poisoning Prevention in Federated Learning and Differential Privacy via Stateful Proofs of Execution
by: Rattanavipanon, Norrathep, et al.
Published: (2024)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
by: Zhou, Shuai, et al.
Published: (2024)

Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
by: Wu, Yu-Hang, et al.
Published: (2025)

Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning
by: Zhang, Xueqing, et al.
Published: (2024)