all InfoSec news
Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model. (arXiv:2206.14371v1 [stat.ML])
June 30, 2022, 1:20 a.m. | Xudong Pan, Yifan Yan, Shengyao Zhang, Mi Zhang, Min Yang
cs.CR updates on arXiv.org arxiv.org
In this paper, we present a novel insider attack called Matryoshka, which
employs an irrelevant scheduled-to-publish DNN model as a carrier model for
covert transmission of multiple secret models which memorize the functionality
of private ML data stored in local data centers. Instead of treating the
parameters of the carrier model as bit strings and applying conventional
steganography, we devise a novel parameter sharing approach which exploits the
learning capacity of the carrier model for information hiding. Matryoshka
simultaneously achieves: …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Technology Specialist II: Network Architect
@ Los Angeles County Employees Retirement Association (LACERA) | Pasadena, CA
Cybersecurity Skills Challenge -- Sponsored by DoD
@ Correlation One | United States
Security Operations Center (SOC) Analyst
@ GK Cybersecurity Group | Remote
DevSecOps Engineer
@ SIXGEN | Remote
Senior DevSecOps Engineer
@ nou Systems, Inc. | Huntsville AL, Huntsville, AL, US
Security Engineer (f/m/d)
@ Enpal B.V. | Berlin, Germany