all InfoSec news
Teacher Model Fingerprinting Attacks Against Transfer Learning. (arXiv:2106.12478v2 [cs.CR] UPDATED)
June 24, 2022, 1:20 a.m. | Yufei Chen, Chao Shen, Cong Wang, Yang Zhang
cs.CR updates on arXiv.org arxiv.org
Transfer learning has become a common solution to address training data
scarcity in practice. It trains a specified student model by reusing or
fine-tuning early layers of a well-trained teacher model that is usually
publicly available. However, besides utility improvement, the transferred
public knowledge also brings potential threats to model confidentiality, and
even further raises other security and privacy issues.
In this paper, we present the first comprehensive investigation of the
teacher model exposure threat in the transfer learning context, …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Network AWS Cloud &Firewall Engineer
@ Arthur Grand Technologies Inc | Plano, TX, United States
Lead Consultant, Data Centre & BCP
@ Singtel | Singapore, Singapore
Protocol Security Engineer
@ Osmosis Labs | Remote
Technical Engineer - Payments Security Specialist
@ H&M Group | Bengaluru, India
Intern, Security Architecture
@ Sony | Work from Home-CA