Cover Image

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yuhao, Qu, Wenjie, Zhai, Shengfang, Jiang, Yanze, Liu, Zichen, Liu, Yue, Dong, Yinpeng, Zhang, Jiaheng
Format:	Preprint
Published:	2025
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

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
by: Wang, Yuhao, et al.
Published: (2026)

Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
by: Zhai, Shengfang, et al.
Published: (2025)

Securing LLM Agents Need Intent-to-Execution Integrity
by: Qu, Wenjie, et al.
Published: (2026)

BadDLM: Backdooring Diffusion Language Models with Diverse Targets
by: Zhai, Shengfang, et al.
Published: (2026)

DMark: Order-Agnostic Watermarking for Diffusion Large Language Models
by: Wu, Linyu, et al.
Published: (2025)

Discovering Universal Semantic Triggers for Text-to-Image Synthesis
by: Zhai, Shengfang, et al.
Published: (2024)

IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
by: Guo, Yanpei, et al.
Published: (2026)

Provably Robust Multi-bit Watermarking for AI-generated Text
by: Qu, Wenjie, et al.
Published: (2024)

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

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
by: Tian, Zhihua, et al.
Published: (2025)

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning
by: Zhu, Zhenhao, et al.
Published: (2025)

BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
by: Li, Hao, et al.
Published: (2025)

S-Leak: Leakage-Abuse Attack Against Efficient Conjunctive SSE via s-term Leakage
by: Su, Yue, et al.
Published: (2025)

ThreatPilot: Attack-Driven Threat Intelligence Extraction
by: Xu, Ming, et al.
Published: (2024)

The Silent Spill: Measuring Sensitive Data Leaks Across Public URL Repositories
by: Ramadan, Tarek, et al.
Published: (2026)

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
by: Zhai, Shengfang, et al.
Published: (2024)

Leaking Queries On Secure Stream Processing Systems
by: Pham, Hung, et al.
Published: (2025)

Prompt Inversion Attack against Collaborative Inference of Large Language Models
by: Qu, Wenjie, et al.
Published: (2025)

Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
by: Qi, Zhisheng, et al.
Published: (2026)

Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems
by: Wang, Weijie, et al.
Published: (2026)

Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
by: Nguyen, Nguyen Linh Bao, et al.
Published: (2026)

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
by: Liu, Tong, et al.
Published: (2024)

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
by: Xue, Jing, et al.
Published: (2025)

Coordinated Position Falsification Attacks and Countermeasures for Location-Based Services
by: Liu, Wenjie, et al.
Published: (2025)

LeakDojo: Decoding the Leakage Threats of RAG Systems
by: Zhang, Maosen, et al.
Published: (2026)

Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
by: Guo, Wei, et al.
Published: (2025)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
by: Wang, Youze, et al.
Published: (2025)

RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
by: Zhao, Tianzhe, et al.
Published: (2025)

Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks
by: Al-Lawati, Ali, et al.
Published: (2026)

Effectiveness of Adversarial Benign and Malware Examples in Evasion and Poisoning Attacks
by: Kozák, Matouš, et al.
Published: (2025)

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
by: Kaneko, Masahiro, et al.
Published: (2025)

Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
by: Chen, Tianyu, et al.
Published: (2025)

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game
by: Xie, Yuanbo, et al.
Published: (2026)

EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling
by: Song, Zichen, et al.
Published: (2024)

ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks
by: Cheng, Zhan, et al.
Published: (2025)

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
by: Liu, Yue, et al.
Published: (2025)

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
by: Huang, Yao, et al.
Published: (2025)

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
by: Li, Jiate, et al.
Published: (2026)

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
by: Xie, Zhixin, et al.
Published: (2025)

A Benign Activity Extraction Method for Malignant Activity Identification using Data Provenance
by: Saito, Taishin
Published: (2025)