Skip to main content
Log in

International Journal of Parallel Programming - Call for Papers Special issue on The Architecture of Processing Encrypted Data. Part I

GUEST EDITORS:

Rosario Cammarota, rosario.cammarota@intel.com (this opens in a new tab), Intel Labs
Chris Wilkerson, chris.wiklerson@intel.com (this opens in a new tab), Intel Labs

AIMS and SCOPE: 

The application of techniques for processing encrypted data, such as fully homomorphic encryption, promises to unleash a new era of high-performance architectures and their compilers that can achieve the pinnacle of data privacy, where data is never decrypted during the data lifecycle even during processing: An Internet web page can be rendered in real-time out of blobs of encrypted data; analytics and advertisements can be monetized without compromising stakeholders privacy; monetization of enterprise data can be achieved with a significant reduction of the risk of third-party data leakage, as well as a reduction of competitive trends leakage.

Processing encrypted data requires a fundamental rethinking of compute and how it interacts with memory and data. Challenges include massive operand and meta data sizes, and simple arithmetic operations like add and multiply may require five orders of magnitude more computing.  Architectures that support these workloads will rely on compute units and a memory hierarchy that optimized for the native processing of encrypted data.  To achieve an acceptable total cost of ownership, such ambitious performance must be delivered within constrained power envelopes and die areas. The software stack must depart from existing reference libraries created for driving proof of concept – the known primary way to program homomorphic encryption on CPU – to suitable and sustainable software stacks to explore the application domain meaningfully with the support of novel hardware architectures. 

TOPICS INTEREST INCLUDE

The topics of interest for this special issue include, but are not limited to, the following topics related to processing encrypted data:

  • Novel micro-architecture designs for including but not limited to fully homomorphic encryption, two- or more-party computation, zero knowledge proofs and combinations thereof.
  • Novel Compilers, run time, and software tools for including but not limited to fully homomorphic encryption, two- or more-party computation, zero-knowledge proofs, and combinations thereof.
  • Toward complete data center solutions integrating including but not limited to fully homomorphic encryption, two- or more-party computation, zero-knowledge proofs, and combinations thereof with existing security solutions.
  • Novel data types and programming languages to capture the essence of processing encrypted data natively.
  • Impact of specific methods and their parameterization on algorithmic co-design. 
  • Benchmarking and metrics of evaluation. End-to-end applications. 
  • Other infrastructure-related aspects include key management, ability, agility to deploy, and sustainability.

Given that the goal of the issue is to provide an authoritative starting point for future research, we encourage authors to provide a comprehensive description of related research and state of practice from the perspectives of high-performance architecture and their compilers for processing encrypted data.

IMPORTANT DATES:

Open for submissions in Springer Manuscripts: March 1, 2023
Closed for submissions: April 1, 2023
Results of first round reviews: June 15, 2023
Submission of revised manuscripts: July 15, 2023
Results of second round reviews: August 15, 2023 Publication material due: September 30, 2023

SUBMISSION GUIDELINES:

Authors should prepare their manuscript according to the Instructions for Authors available from the International Journal of Parallel Programming website (this opens in a new tab). Authors should submit through the online submission site  (this opens in a new tab) and select “SI Special issue on The Architecture of Processing Encrypted Data. Part I" when they reach the “Article Type” step in the submission process. Submitted papers should present original, unpublished work, relevant to the topics of the special issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least three independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process. Final decisions on all papers are made by the Editor in Chief.

Navigation