All Your Knowledge Belongs to Us: Stealing Knowledge Graphs via Reasoning APIs

• URL: http://arxiv.org/abs/2503.09727v1
• Date: Wed, 12 Mar 2025 18:18:44 GMT
• Title: All Your Knowledge Belongs to Us: Stealing Knowledge Graphs via Reasoning APIs
• Authors: Zhaohan Xi,
• Abstract summary: We present KGX, an attack that extracts confidential sub-KGs with high fidelity under limited query budgets.<n>We validate the efficacy of KGX against both experimental and real-world KGR APIs.<n>Our findings suggest the need for a more principled approach to developing and deploying KGR systems.
• Score: 7.685940197285116
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge graph reasoning (KGR), which answers complex, logical queries over large knowledge graphs (KGs), represents an important artificial intelligence task with a range of applications. Many KGs require extensive domain expertise and engineering effort to build and are hence considered proprietary within organizations and enterprises. Yet, spurred by their commercial and research potential, there is a growing trend to make KGR systems, (partially) built upon private KGs, publicly available through reasoning APIs. The inherent tension between maintaining the confidentiality of KGs while ensuring the accessibility to KGR systems motivates our study of KG extraction attacks: the adversary aims to "steal" the private segments of the backend KG, leveraging solely black-box access to the KGR API. Specifically, we present KGX, an attack that extracts confidential sub-KGs with high fidelity under limited query budgets. At a high level, KGX progressively and adaptively queries the KGR API and integrates the query responses to reconstruct the private sub-KG. This extraction remains viable even if any query responses related to the private sub-KG are filtered. We validate the efficacy of KGX against both experimental and real-world KGR APIs. Interestingly, we find that typical countermeasures (e.g., injecting noise into query responses) are often ineffective against KGX. Our findings suggest the need for a more principled approach to developing and deploying KGR systems, as well as devising new defenses against KG extraction attacks.

Related papers

• Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness [25.74411097212245]
  Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) is a technique that enhances Large Language Model (LLM) inference in tasks like Question Answering (QA) Existing benchmarks do not adequately capture the impact of KG incompleteness on KG-RAG performance. We demonstrate that KG-RAG methods are sensitive to KG incompleteness, highlighting the need for more robust approaches in realistic settings.
  arXiv  Detail & Related papers  (2025-04-07T15:08:03Z)
• Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains [66.55612528039894]
  Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) We present DoG (Decoding on Graphs), a novel framework that facilitates a deep synergy between LLMs and KGs. Experiments across various KGQA tasks with different background KGs demonstrate that DoG achieves superior and robust performance.
  arXiv  Detail & Related papers  (2024-10-24T04:01:40Z)
• Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models [83.28737898989694]
  Large language models (LLMs) struggle with faithful reasoning due to knowledge gaps and hallucinations. We introduce graph-constrained reasoning (GCR), a novel framework that bridges structured knowledge in KGs with unstructured reasoning in LLMs. GCR achieves state-of-the-art performance and exhibits strong zero-shot generalizability to unseen KGs without additional training.
  arXiv  Detail & Related papers  (2024-10-16T22:55:17Z)
• SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs [32.93944146681218]
  We propose a general KG construction framework, named SAC-KG, to exploit large language models (LLMs) as Skilled Automatic Constructors for domain Knowledge Graph. SAC-KG effectively involves LLMs as domain experts to generate specialized and precise multi-level KGs. Experiments demonstrate that SAC-KG automatically constructs a domain KG at the scale of over one million nodes and achieves a precision of 89.32%.
  arXiv  Detail & Related papers  (2024-09-22T13:55:23Z)
• Context Graph [8.02985792541121]
  We present a context graph reasoning textbfCGR$3$ paradigm that leverages large language models (LLMs) to retrieve candidate entities and related contexts. Our experimental results demonstrate that CGR$3$ significantly improves performance on KG completion (KGC) and KG question answering (KGQA) tasks.
  arXiv  Detail & Related papers  (2024-06-17T02:59:19Z)
• Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering [87.67177556994525]
  We propose a training-free method called Generate-on-Graph (GoG) to generate new factual triples while exploring Knowledge Graphs (KGs) GoG performs reasoning through a Thinking-Searching-Generating framework, which treats LLM as both Agent and KG in IKGQA.
  arXiv  Detail & Related papers  (2024-04-23T04:47:22Z)
• Federated Neural Graph Databases [53.03085605769093]
  We propose Federated Neural Graph Database (FedNGDB), a novel framework that enables reasoning over multi-source graph-based data while preserving privacy. Unlike existing methods, FedNGDB can handle complex graph structures and relationships, making it suitable for various downstream tasks.
  arXiv  Detail & Related papers  (2024-02-22T14:57:44Z)
• Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph [64.42060648398743]
  We introduce the process of building an open business knowledge graph (OpenBG) derived from a well-known enterprise, Alibaba Group. OpenBG is an open business KG of unprecedented scale: 2.6 billion triples with more than 88 million entities covering over 1 million core classes/concepts and 2,681 types of relations.
  arXiv  Detail & Related papers  (2022-09-30T04:03:26Z)
• Reasoning over Multi-view Knowledge Graphs [59.99051368907095]
  ROMA is a novel framework for answering logical queries over multi-view KGs. It scales up to KGs of large sizes (e.g., millions of facts) and fine-granular views. It generalizes to query structures and KG views that are unobserved during training.
  arXiv  Detail & Related papers  (2022-09-27T21:32:20Z)
• Knowledge Graph Curation: A Practical Framework [0.0]
  We propose a practical knowledge graph curation framework for improving the quality of KGs. First, we define a set of quality metrics for assessing the status of KGs. Second, we describe the verification and validation of KGs as cleaning tasks. Third, we present duplicate detection and knowledge fusion strategies for enriching KGs.
  arXiv  Detail & Related papers  (2022-08-17T07:55:28Z)
• Collaborative Knowledge Graph Fusion by Exploiting the Open Corpus [59.20235923987045]
  It is challenging to enrich a Knowledge Graph with newly harvested triples while maintaining the quality of the knowledge representation. This paper proposes a system to refine a KG using information harvested from an additional corpus.
  arXiv  Detail & Related papers  (2022-06-15T12:16:10Z)
• Survey and Open Problems in Privacy Preserving Knowledge Graph: Merging, Query, Representation, Completion and Applications [17.68925521011772]
  Knowledge Graph (KG) has attracted more and more companies' attention for its ability to connect different types of data in meaningful ways. However, the data isolation problem limits the performance of KG and prevents its further development. How to conduct privacy preserving KG becomes an important research question to answer.
  arXiv  Detail & Related papers  (2020-11-20T02:35:47Z)
• IterefinE: Iterative KG Refinement Embeddings using Symbolic Knowledge [10.689559910656474]
  Knowledge Graphs (KGs) extracted from text sources are often noisy and lead to poor performance in downstream application tasks such as KG-based question answering. Most successful techniques for KG refinement make use of inference rules and reasoning oversupervised. In this paper, we present a KG refinement framework called IterefinE which iteratively combines the two techniques.
  arXiv  Detail & Related papers  (2020-06-03T14:05:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.