Data protection in AI services: A survey

C Meurisch, M Mühlhäuser - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
Advances in artificial intelligence (AI) have shaped today's user services, enabling
enhanced personalization and better support. As such AI-based services inevitably require …

On protecting the data privacy of large language models (llms): A survey

B Yan, K Li, M Xu, Y Dong, Y Zhang, Z Ren… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) are complex artificial intelligence systems capable of
understanding, generating and translating human language. They learn language patterns …

A group signature scheme with selective linkability and traceability for blockchain-based data sharing systems in e-health services

Z Bao, D He, H Wang, M Luo… - IEEE Internet of Things …, 2023 - ieeexplore.ieee.org
Recently, with the rapid improvement of e-health technology, a large amount of precious
medical data has been accumulated in different entities, such as hospitals, clinics, and …

AirGapAgent: Protecting privacy-conscious conversational agents

E Bagdasarian, R Yi, S Ghalebikesabi… - Proceedings of the …, 2024 - dl.acm.org
The growing use of large language model (LLM)-based conversational agents to manage
sensitive user data raises significant privacy concerns. While these agents excel at …

Operationalizing contextual integrity in privacy-conscious assistants

S Ghalebikesabi, E Bagdasaryan, R Yi, I Yona… - arxiv preprint arxiv …, 2024 - arxiv.org
Advanced AI assistants combine frontier LLMs and tool access to autonomously perform
complex tasks on behalf of users. While the helpfulness of such assistants can increase …

Exsense: Extract sensitive information from unstructured data

Y Guo, J Liu, W Tang, C Huang - Computers & Security, 2021 - Elsevier
Large-scale sensitive information leakage incidents are frequently reported in recent years.
Once sensitive information is leaked, it may lead to serious effects. In this context, sensitive …

Privacy-preserving AI services through data decentralization

C Meurisch, B Bayrak, M Mühlhäuser - Proceedings of The Web …, 2020 - dl.acm.org
User services increasingly base their actions on AI models, eg, to offer personalized and
proactive support. However, the underlying AI algorithms require a continuous stream of …

Automating governing knowledge commons and contextual integrity (GKC-CI) privacy policy annotations with large language models

J Chanenson, M Pickering, N Apthorpe - arxiv preprint arxiv:2311.02192, 2023 - arxiv.org
Identifying contextual integrity (CI) and governing knowledge commons (GKC) parameters in
privacy policy texts can facilitate normative privacy analysis. However, GKC-CI annotation …

On Data Leakage Prevention Maturity: Adapting the C2M2 Framework

J Domnik, A Holland - Journal of Cybersecurity and Privacy, 2024 - mdpi.com
In an evolving cybersecurity landscape marked by escalating data breaches and regulatory
demands, data leakage prevention (DLP) has emerged as one of several defense …

Detection and prevention of data leakage in transit using LSTM recurrent neural network with encryption algorithm

MK Abiodun, AE Adeniyi, AO Victor… - … and Business for …, 2023 - ieeexplore.ieee.org
As the amount of data generated by organizations continues to multiply, there is a need to
ensure the security and transmission of these data at any stage that they may be at. Data …