Advancing Design and Runtime Management of AI Applications with AI-SPRINT
Research output: Contribution to conferences › Paper › Contributed › peer-review
Contributors
Abstract
The adoption of Artificial intelligence (AI) technologies is steadily in-
creasing. However, to become fully pervasive, AI needs resources at the
edge of the network. The cloud can provide the processing power needed
for big data, but edge computing is close to where data are produced
and therefore crucial to their timely, flexible, and secure management. In
this paper, we introduce the AI-SPRINT “Artificial intelligence in Secure
PRIvacy-preserving computing coNTinuum” project, which will provide
solutions to seamlessly design, partition, and run AI applications in com-
puting continuum environments. AI-SPRINT will offer novel tools for AI
applications development, secure execution, easy deployment, as well as
runtime management and optimization: AI-SPRINT design tools will al-
low trading-off application performance (in terms of end-to-end latency or
throughput), energy efficiency, and AI models accuracy while providing
security and privacy guarantees. The runtime environment will support
live data protection, architecture enhancement, agile delivery, runtime
optimization, and continuous adaptation.
creasing. However, to become fully pervasive, AI needs resources at the
edge of the network. The cloud can provide the processing power needed
for big data, but edge computing is close to where data are produced
and therefore crucial to their timely, flexible, and secure management. In
this paper, we introduce the AI-SPRINT “Artificial intelligence in Secure
PRIvacy-preserving computing coNTinuum” project, which will provide
solutions to seamlessly design, partition, and run AI applications in com-
puting continuum environments. AI-SPRINT will offer novel tools for AI
applications development, secure execution, easy deployment, as well as
runtime management and optimization: AI-SPRINT design tools will al-
low trading-off application performance (in terms of end-to-end latency or
throughput), energy efficiency, and AI models accuracy while providing
security and privacy guarantees. The runtime environment will support
live data protection, architecture enhancement, agile delivery, runtime
optimization, and continuous adaptation.
Details
| Original language | English |
|---|---|
| Number of pages | 17 |
| Publication status | Published - Jun 2021 |
| Peer-reviewed | Yes |
Conference
| Title | Default Cover Image 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC) |
|---|---|
| Conference number | |
| Duration | 12 - 16 July 2021 |
| Website | |
| Degree of recognition | International event |
| Location | |
| City | Madrid |
| Country | Spain |
External IDs
| Scopus | 85115868821 |
|---|
Keywords
Research priority areas of TU Dresden
DFG Classification of Subject Areas according to Review Boards
Sustainable Development Goals
Keywords
- Cloud computing, og computing, edge computin, AI and machine learning, Cloud trust security & privacy, Cloud computing, fog computing, edge computing, AI and machine learning, Cloud trust security & privacy, big data, AI-SPRINT project, AI applications development, runtime management, AI-SPRINT design tools, runtime environment, data protection, runtime optimization, artificial intelligence technologies, artificial intelligence, data flow analysis, security of data, Privacy, Computational modeling, Biological system modeling