all InfoSec news
FBI: Fingerprinting models with Benign Inputs. (arXiv:2208.03169v1 [cs.CR])
Aug. 8, 2022, 1:20 a.m. | Thibault Maho, Teddy Furon, Erwan Le Merrer
cs.CR updates on arXiv.org arxiv.org
Recent advances in the fingerprinting of deep neural networks detect
instances of models, placed in a black-box interaction scheme. Inputs used by
the fingerprinting protocols are specifically crafted for each precise model to
be checked for. While efficient in such a scenario, this nevertheless results
in a lack of guarantee after a mere modification (like retraining,
quantization) of a model. This paper tackles the challenges to propose i)
fingerprinting schemes that are resilient to significant modifications of the
models, by …
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
Information Security Engineers
@ D. E. Shaw Research | New York City
Cybersecurity Engineer
@ Alstom | Charleroi, BE
Member of Compliance, Information Technology
@ Anchorage Digital | United States
Information Security Consultant (GRC) - Cumulus Systems
@ Hitachi | (HIL) DELHI - RHQ
Security Engineer
@ EarnIn | Mexico