Seeing is believing: Black-box membership inference attacks against retrieval augmented generation

[PDF] arxiv.org

Security matrix for multimodal agents on mobile devices: A systematic and proof of concept study

Y Yang, X Yang, S Li, C Lin, Z Zhao, C Shen… - arXiv preprint arXiv …, 2024 - arxiv.org
The rapid progress in the reasoning capability of the Multi-modal Large Language Models
(MLLMs) has triggered the development of autonomous agent systems on mobile devices …
被引用次数：5 相关文章 所有 3 个版本
[PDF] arxiv.org

Mask-based Membership Inference Attacks for Retrieval-Augmented Generation

M Liu, S Zhang, C Long - arXiv preprint arXiv:2410.20142, 2024 - arxiv.org
Retrieval-Augmented Generation (RAG) has been an effective approach to mitigate
hallucinations in large language models (LLMs) by incorporating up-to-date and domain …
被引用次数：1 相关文章 所有 2 个版本
[PDF] arxiv.org

Unleashing worms and extracting data: Escalating the outcome of attacks against rag-based inference in scale and severity using jailbreaking

S Cohen, R Bitton, B Nassi - arXiv preprint arXiv:2409.08045, 2024 - arxiv.org
In this paper, we show that with the ability to jailbreak a GenAI model, attackers can escalate
the outcome of attacks against RAG-based GenAI-powered applications in severity and …
被引用次数：2 相关文章 所有 3 个版本
[PDF] arxiv.org

Membership Inference Attack against Long-Context Large Language Models

Z Wang, G Liu, Y Yang, C Wang - arXiv preprint arXiv:2411.11424, 2024 - arxiv.org
Recent advances in Large Language Models (LLMs) have enabled them to overcome their
context window limitations, and demonstrate exceptional retrieval and reasoning capacities …
相关文章 所有 2 个版本
[PDF] arxiv.org

SoK: Unifying Cybersecurity and Cybersafety of Multimodal Foundation Models with an Information Theory Approach

R Sun, J Chang, H Pearce, C Xiao, B Li, Q Wu… - arXiv preprint arXiv …, 2024 - arxiv.org
Multimodal foundation models (MFMs) represent a significant advancement in artificial
intelligence, combining diverse data modalities to enhance learning and understanding …
相关文章 所有 2 个版本
[PDF] arxiv.org

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

C Di Maio, C Cosci, M Maggini, V Poggioni… - arXiv preprint arXiv …, 2024 - arxiv.org
The growing ubiquity of Retrieval-Augmented Generation (RAG) systems in several real-
world services triggers severe concerns about their security. A RAG system improves the …
相关文章 所有 2 个版本
[PDF] nii.ac.jp

検索拡張生成(RAG) は大規模言語モデルからの学習データ漏洩リスクを軽減するのか?

中井綱人， 東拓矢， 大西健斗 - コンピュータセキュリティシンポジウム …, 2024 - ipsj.ixsq.nii.ac.jp
論文抄録 検索拡張生成 (RAG) は, 外部知識データベース (リトリーバルデータベース)
から関連知識を取得することで, 大規模言語モデルの学習効率, 知識更新, 信頼性を強化する技術 …
相关文章 所有 3 个版本