Privacy-Preserving Synthetic Data Generation Method for IoT-Sensor Network IDS Using CTGAN
Saleh Alabdulwahab, Young-Tak Kim, Yunsik Son, Isaac Woungang, Wei Lu · 2024
Read Privacy-Preserving Synthetic Data Generation Method for IoT-Sensor Network IDS Using CTGAN by Saleh Alabdulwahab, Young-Tak Kim, Yunsik Son, Isaac Woungang, Wei Lu (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11598811.txt.
Description
Saleh Alabdulwahab and co-authors published a 2024 study of a way to generate synthetic sensor network data so that security tools can train on it with no real data at risk. Networks of linked sensors now watch homes and workplaces. Their intrusion detection tools learn from large sets of past traffic, and those sets are most often held by third parties.
The method creates synthetic data with CTGAN, a two-network generative method tuned for tables. A controlled dose of noise is mixed in to shield each real record. Two adjustments keep the shape of the synthetic set close to the real one. The synthetic set scored high on a known statistical test, well past plain noise methods. It also held off the known privacy attacks: singling out, linking, and inference. The team says networks can train their guards on such synthetic data with low risk.
Catalog record
| CREATOR | Saleh Alabdulwahab, Young-Tak Kim, Yunsik Son, Isaac Woungang, Wei Lu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |