Authors: Oleksandr Kuznetsov, Dmytro Zakharov, Emanuele Frontoni, Andrea Maranesi

Published on: February 06, 2024

Impact Score: 8.45

Arxiv code: Arxiv:2402.03769

Summary

• What is new: Introduces AttackNet, a new Convolutional Neural Network architecture designed to counteract spoofing in biometric systems more effectively than existing models.
• Why this is important: The integrity and reliability of biometric samples are increasingly undermined by spoofing threats.
• What the research proposes: AttackNet employs a bespoke architecture that improves detection of spoofing through layered defense mechanisms, from low-level feature extraction to high-level pattern discernment.
• Results: AttackNet demonstrates superior performance metrics compared to contemporary models across diverse datasets.

Technical Details

Technological frameworks used: AttackNet, a Convolutional Neural Network

Models used: nan

Data used: Diverse datasets for benchmarking

Potential Impact

Biometric security providers, identity verification services, sectors relying on biometric authentication (finance, healthcare, security)

Want to implement this idea in a business?

We have generated a startup concept here: SafeIDGuard.