1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Effectiveness Of Random Deep Feature Selection For Securing Image Manipulation Detectors Against Adversarial Examples

Effectiveness Of Random Deep Feature Selection For Securing Image Manipulation Detectors Against Adversarial Examples

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

We investigate if the random feature selection approach proposed in \cite{chen2019secure} to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transf

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Effectiveness Of Random Deep Feature Selection For Securing Image Manipulation Detectors Against Adversarial Examples

00:14:13

0 views

We investigate if the random feature selection approach proposed in cite{chen2019secure} to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transf