Ai agents under threat: A survey of key security challenges and future pathways

Z Deng, Y Guo, C Han, W Ma, J **ong, S Wen… - ACM Computing …, 2024 - dl.acm.org
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or
makes decisions based on pre-defined objectives and data inputs. AI agents, capable of …

A survey on rag meeting llms: Towards retrieval-augmented large language models

W Fan, Y Ding, L Ning, S Wang, H Li, D Yin… - Proceedings of the 30th …, 2024 - dl.acm.org
As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can
offer reliable and up-to-date external knowledge, providing huge convenience for numerous …

Unique security and privacy threats of large language model: A comprehensive survey

S Wang, T Zhu, B Liu, M Ding, X Guo, D Ye… - arxiv preprint arxiv …, 2024 - arxiv.org
With the rapid development of artificial intelligence, large language models (LLMs) have
made remarkable advancements in natural language processing. These models are trained …

[PDF][PDF] Trustworthiness in retrieval-augmented generation systems: A survey

Y Zhou, Y Liu, X Li, J **, H Qian, Z Liu, C Li… - arxiv preprint arxiv …, 2024 - zhouyujia.cn
Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the
development of Large Language Models (LLMs). While much of the current research in this …

Is my data in your retrieval database? membership inference attacks against retrieval augmented generation

M Anderson, G Amit, A Goldsteen - arxiv preprint arxiv:2405.20446, 2024 - arxiv.org
Retrieval Augmented Generation (RAG) systems have shown great promise in natural
language processing. However, their reliance on data stored in a retrieval database, which …

Blockchain for large language model security and safety: A holistic survey

C Geren, A Board, GG Dagher, T Andersen… - ACM SIGKDD …, 2025 - dl.acm.org
With the growing development and deployment of large language models (LLMs) in both
industrial and academic fields, their security and safety concerns have become increasingly …

Here comes the AI worm: Unleashing zero-click worms that target GenAI-powered applications

S Cohen, R Bitton, B Nassi - arxiv preprint arxiv:2403.02817, 2024 - arxiv.org
In the past year, numerous companies have incorporated Generative AI (GenAI) capabilities
into new and existing applications, forming interconnected Generative AI (GenAI) …

Mitigating the privacy issues in retrieval-augmented generation (rag) via pure synthetic data

S Zeng, J Zhang, P He, J Ren, T Zheng, H Lu… - arxiv preprint arxiv …, 2024 - arxiv.org
Retrieval-augmented generation (RAG) enhances the outputs of language models by
integrating relevant information retrieved from external knowledge sources. However, when …

Rag-thief: Scalable extraction of private data from retrieval-augmented generation applications with agent-based attacks

C Jiang, X Pan, G Hong, C Bao, M Yang - arxiv preprint arxiv:2411.14110, 2024 - arxiv.org
While large language models (LLMs) have achieved notable success in generative tasks,
they still face limitations, such as lacking up-to-date knowledge and producing …

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 …