Copertina

Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Di Maio, Christian, Cosci, Cristian, Maggini, Marco, Poggioni, Valentina, Melacci, Stefano
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Neuro-Symbolic Framework for Sequence Classification with Relational and Temporal Knowledge
di: Lorello, Luca Salvatore, et al.
Pubblicazione: (2025)

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries
di: Wang, Yuhao, et al.
Pubblicazione: (2025)

Bridging OLAP and RAG: A Multidimensional Approach to the Design of Corpus Partitioning
di: Maio, Dario, et al.
Pubblicazione: (2026)

The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns
di: Lorello, Luca Salvatore, et al.
Pubblicazione: (2024)

LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoning
di: Lorello, Luca Salvatore, et al.
Pubblicazione: (2025)

LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks
di: Panebianco, Francesco, et al.
Pubblicazione: (2025)

Harnessing LLMs for Educational Content-Driven Italian Crossword Generation
di: Zeinalipour, Kamyar, et al.
Pubblicazione: (2024)

Generative System Dynamics in Recurrent Neural Networks
di: Casoni, Michele, et al.
Pubblicazione: (2025)

LeakBoost: Perceptual-Loss-Based Membership Inference Attack
di: Taub, Amit Kravchik, et al.
Pubblicazione: (2026)

A Unified Framework for Neural Computation and Learning Over Time
di: Melacci, Stefano, et al.
Pubblicazione: (2024)

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

Multitask Kernel-based Learning with Logic Constraints
di: Diligenti, Michelangelo, et al.
Pubblicazione: (2024)

Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study
di: Jain, Amay, et al.
Pubblicazione: (2025)

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

ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications
di: Zeinalipour, Kamyar, et al.
Pubblicazione: (2023)

Digital and Web Forensics Model Cards, V1
di: Di Maio, Paola
Pubblicazione: (2025)

Towards Open Standards for Systemic Complexity in Digital Forensics
di: Di Maio, Paola
Pubblicazione: (2025)

Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles
di: Zugarini, Andrea, et al.
Pubblicazione: (2024)

When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation
di: Ward, Joshua, et al.
Pubblicazione: (2025)

Multitask Kernel-based Learning with First-Order Logic Constraints
di: Diligenti, Michelangelo, et al.
Pubblicazione: (2023)

Enhanced Water Leak Detection with Convolutional Neural Networks and One-Class Support Vector Machine
di: Leonzio, Daniele Ugo, et al.
Pubblicazione: (2025)

Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
di: Marinelli, Ryan, et al.
Pubblicazione: (2025)

Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention
di: Dekel, Sagie, et al.
Pubblicazione: (2026)

When Benchmarks Leak: Inference-Time Decontamination for LLMs
di: Chai, Jianzhe, et al.
Pubblicazione: (2026)

Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering
di: Liu, Xukai, et al.
Pubblicazione: (2025)

Design Proteins Using Large Language Models: Enhancements and Comparative Analyses
di: Zeinalipour, Kamyar, et al.
Pubblicazione: (2024)

Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
di: Chen, Yingjian, et al.
Pubblicazione: (2025)

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
di: Li, Jianan, et al.
Pubblicazione: (2026)

RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
di: Xu, Ran, et al.
Pubblicazione: (2025)

KERAIA: An Adaptive and Explainable Framework for Dynamic Knowledge Representation and Reasoning
di: Varey, Stephen Richard, et al.
Pubblicazione: (2025)

Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuning
di: Maggini, Michele Joshua, et al.
Pubblicazione: (2025)

PLeak: Prompt Leaking Attacks against Large Language Model Applications
di: Hui, Bo, et al.
Pubblicazione: (2024)

Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts
di: Mächtle, Felix, et al.
Pubblicazione: (2025)

AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases
di: Suresh, Susheel, et al.
Pubblicazione: (2026)

Knowledge-Graph Based RAG System Evaluation Framework
di: Dong, Sicheng, et al.
Pubblicazione: (2025)

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
di: Wu, Yutao, et al.
Pubblicazione: (2025)

Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
di: Balloccu, Simone, et al.
Pubblicazione: (2024)

BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts
di: Lyu, Xiaoting, et al.
Pubblicazione: (2026)

LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
di: Zhang, Yaoze, et al.
Pubblicazione: (2025)

Adaptive Financial Sentiment Analysis for NIFTY 50 via Instruction-Tuned LLMs , RAG and Reinforcement Learning Approaches
di: Chaithra, et al.
Pubblicazione: (2025)