Cover Image

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Wuyang, Pei, Shichao
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
by: Das, Debeshee, et al.
Published: (2026)

Your Agent Can Defend Itself against Backdoor Attacks
by: Changjiang, Li, et al.
Published: (2025)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
by: Yang, Wenkai, et al.
Published: (2024)

Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
by: Croce, Nicola, et al.
Published: (2025)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
by: Chen, Zhuowei, et al.
Published: (2025)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, et al.
Published: (2025)

WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes
by: Valbuena, Victor
Published: (2024)

Can Large Language Models Really Recognize Your Name?
by: Pham, Dzung, et al.
Published: (2025)

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
by: Liang, Zi, et al.
Published: (2025)

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
by: Jiang, Yukun, et al.
Published: (2026)

VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Traces
by: Grigor, Artem, et al.
Published: (2025)

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
by: Qiao, Yuxuan, et al.
Published: (2025)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
by: Zhu, Pengyu, et al.
Published: (2025)

Do Phone-Use Agents Respect Your Privacy?
by: Tang, Zhengyang, et al.
Published: (2026)

OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
by: Wang, Longxiang, et al.
Published: (2026)

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
by: Jiao, Ruochen, et al.
Published: (2024)

Can You Trust Your Copilot? A Privacy Scorecard for AI Coding Assistants
by: AL-Maamari, Amir
Published: (2025)

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
by: Yu, Haiyang, et al.
Published: (2024)

Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers
by: Chen, Simin, et al.
Published: (2025)

RedacBench: Can AI Erase Your Secrets?
by: Jeon, Hyunjun, et al.
Published: (2026)

Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace
by: Lan, Qianlong, et al.
Published: (2026)

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

DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
by: Popovic, Dorde, et al.
Published: (2025)

Dark Distillation: Backdooring Distilled Datasets without Accessing Raw Data
by: Yang, Ziyuan, et al.
Published: (2025)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
by: Sneh, Jonathan, et al.
Published: (2025)

Protect Your Secrets: Understanding and Measuring Data Exposure in VSCode Extensions
by: Liu, Yue, et al.
Published: (2024)

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
by: Ge, Huaizhi, et al.
Published: (2024)

Clean-Label Physical Backdoor Attacks with Data Distillation
by: Dao, Thinh, et al.
Published: (2024)

Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
by: Wu, Ruihan, et al.
Published: (2025)

You Can Backdoor Personalized Federated Learning
by: Ye, Tiandi, et al.
Published: (2023)

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
by: Foerster, Hanna, et al.
Published: (2026)

How Catastrophic is Your LLM? Certifying Risk in Conversation
by: Wang, Chengxiao, et al.
Published: (2025)

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
by: Ponomareva, Natalia, et al.
Published: (2025)

Evasion-Resilient Detection of DNS-over-HTTPS Data Exfiltration: A Practical Evaluation and Toolkit
by: Elaoumari, Adam
Published: (2025)

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
by: Zhou, Kaiyu, et al.
Published: (2026)

CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack
by: Xia, Hanfeng, et al.
Published: (2024)

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
by: Yang, Chenglin
Published: (2026)

Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World
by: Sadasivan, Vinu Sankar, et al.
Published: (2025)

BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator
by: Zhang, Ruyi, et al.
Published: (2026)

What is in Your Safe Data? Identifying Benign Data that Breaks Safety
by: He, Luxi, et al.
Published: (2024)