Svoboda | Graniru | BBC Russia | Golosameriki | Facebook
 
 

New Trends in Cryptography, Data Security and Privacy with Robust Authentication and Access Control

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 15 October 2024 | Viewed by 961

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong 518057, China
Interests: AI security and privacy

E-Mail Website
Guest Editor
College of Cyber Science and Engineering, Sichuan University, Chengdu 610064, China
Interests: applied cryptography; AI security and privacy

E-Mail Website
Guest Editor
School of Computing and Information Systems, Singapore Management University, Singapore 188065, Singapore
Interests: applied cryptography; access control; auhentication

Special Issue Information

Dear Colleagues,

In today's rapidly evolving digital landscape, safeguarding sensitive private information and digital property is of utmost importance, and cryptography stands as a cornerstone in this sphere, while fine-grain access control and reliable authentication mechanisms play pivotal roles in fortifying data privacy and security, especially for big data-driven applications.

This Special Issue, hosted by the Electronics journal, as part the section on Computer Science, seeks to explore emerging trends in cryptography, data security, and privacy with a specific focus on fine-grain access control and reliable authentication. We invite researchers and practitioners to contribute original research papers, review articles, and case studies that advance the state-of-the-art in crypto-based data privacy and security research. Topics of interest include novel cryptographic protocols, algorithms, and implementation of real-world systems like AI models and cyber-physical systems. By fostering interdisciplinary collaboration and promoting the development of innovative solutions, we aim to pave the way for more secure, privacy-preserving, and reliable digital information systems.

Submissions should align with the scope of the Special Issue and contribute to the advancement of knowledge in this critical domain, with the list of possible topics for this Special Issue including, but not being limited to:

- Access control encryption;

- Fine-grined access control;

- Multi-factor authentication;

- Context-aware authentication;

- Access control and authentication for encrypted data;

- Private computing;

- Secure multiparty computation;

- Crypo-based AI model security;

- Privacy-preserving inference;

- Secure and privacy-preserving distributed/fedearted learning.

We look forward to receiving your contributions.

Dr. Guowen Xu
Dr. Hao Ren
Dr. Jianfei Sun
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • applied cryptograph
  • data security and privacy
  • access control and authentication

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 2967 KiB  
Article
Data Stealing Attacks against Large Language Models via Backdooring
by Jiaming He, Guanyu Hou, Xinyue Jia, Yangyang Chen, Wenqi Liao, Yinhang Zhou and Rang Zhou
Electronics 2024, 13(14), 2858; https://doi.org/10.3390/electronics13142858 - 19 Jul 2024
Viewed by 662
Abstract
Large language models (LLMs) have gained immense attention and are being increasingly applied in various domains. However, this technological leap forward poses serious security and privacy concerns. This paper explores a novel approach to data stealing attacks by introducing an adaptive method to [...] Read more.
Large language models (LLMs) have gained immense attention and are being increasingly applied in various domains. However, this technological leap forward poses serious security and privacy concerns. This paper explores a novel approach to data stealing attacks by introducing an adaptive method to extract private training data from pre-trained LLMs via backdooring. Our method mainly focuses on the scenario of model customization and is conducted in two phases, including backdoor training and backdoor activation, which allow for the extraction of private information without prior knowledge of the model’s architecture or training data. During the model customization stage, attackers inject the backdoor into the pre-trained LLM by poisoning a small ratio of the training dataset. During the inference stage, attackers can extract private information from the third-party knowledge database by incorporating the pre-defined backdoor trigger. Our method leverages the customization process of LLMs, injecting a stealthy backdoor that can be triggered after deployment to retrieve private data. We demonstrate the effectiveness of our proposed attack through extensive experiments, achieving a notable attack success rate. Extensive experiments demonstrate the effectiveness of our stealing attack in popular LLM architectures, as well as stealthiness during normal inference. Full article
Show Figures

Figure 1

Back to TopTop